© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4329
    Prev
    Next
    INDEX
    Explanations

    Specifically, the `<internalType: "address", name: "_policyHolder", type: "address">` suggests a potential pattern related to programming/coding structures, perhaps describing variable types or data formats.The `<TOP_POSITIVE_LOGITS>` list contains words like `indicative`, `indicar`, `indique`, and `asseg` (likely from 'assegnare' or similar in Romance languages, meaning to assign or indicate). `appel` and `Burgos` are outliers.`internalType` definition patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    1.37
    et
    1.35
    ers
    1.33
    ed
    1.32
    es
    1.17
     płyt
    1.15
    em
    1.14
    eners
    1.12
    orphous
    1.11
    ре
    1.10
    POSITIVE LOGITS
     indicative
    1.21
     appel
    1.20
     indicar
    1.19
     enseign
    1.19
     accad
    1.18
     indique
    1.17
    ا
    1.14
    burgo
    1.10
    Portale
    1.09
     asseg
    1.08
    Activations Density 0.000%

    No Known Activations