© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4402
    Prev
    Next
    INDEX
    Explanations

    simple examples, lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     reception
    1.31
    abic
    1.25
     receptions
    1.12
    貰
    1.09
    佯
    1.05
    apollo
    1.05
    Acetoxy
    1.05
    ibar
    1.05
    @
    1.04
    Reception
    1.03
    POSITIVE LOGITS
    दुर्ग
    1.06
    Should
    1.06
     Should
    1.03
    Must
    1.02
     Stoff
    1.01
     Must
    0.96
     luj
    0.95
     болез
    0.94
     ska
    0.94
    لط
    0.93
    Activations Density 0.060%

    No Known Activations