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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 164
    Prev
    Next
    INDEX
    Explanations

    Jr and "the Third"

    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
    ა
    1.86
    atakse
    1.67
    ם
    1.67
    lı
    1.63
    zelfde
    1.63
    ли
    1.63
    리
    1.63
    티
    1.56
    ری
    1.55
    ným
    1.55
    POSITIVE LOGITS
    ,
    1.32
    ire
    1.30
    ills
    1.28
    its
    1.24
    ots
    1.23
    ie
    1.22
    ens
    1.20
     retractable
    1.20
    é
    1.20
    ort
    1.18
    Activations Density 0.009%

    No Known Activations