© 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-262K
    7. 42770
    Prev
    Next
    INDEX
    Explanations

    documentary

    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_262k_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
    ار
    1.58
    ek
    1.53
    наў
    1.34
    أ
    1.31
    ين
    1.26
    ند
    1.26
    DEBUGFS
    1.25
    ai
    1.21
    ູ່
    1.18
    uerte
    1.16
    POSITIVE LOGITS
    1.59
    foods
    1.25
     जस
    1.22
    y
    1.22
    yoga
    1.21
    film
    1.18
    shows
    1.15
    岖
    1.14
     або
    1.13
     Та
    1.12
    Activations Density 0.006%

    No Known Activations