© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 70071
    Prev
    Next
    INDEX
    Explanations

    pygame java awt

    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_15_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
    zęd
    0.87
     vanligt
    0.85
    諧
    0.83
     jí
    0.80
    原地
    0.80
     yapan
    0.77
    dessous
    0.77
     Reinh
    0.76
     ister
    0.76
    pseud
    0.76
    POSITIVE LOGITS
     blacks
    1.68
     photographic
    1.66
    ledge
    1.62
     iconography
    1.62
    +...+
    1.61
     syntactic
    1.60
     pastes
    1.60
     warships
    1.60
     MSA
    1.60
     eyeliner
    1.60
    Activations Density 0.001%

    No Known Activations