© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127047
    Prev
    Next
    INDEX
    Explanations

    lists or topics

    np_acts-logits-general · gemini-2.5-flash-lite

    what if challenge transformed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ');
    0.48
    program
    0.44
    ();
    0.42
    roll
    0.40
    ourses
    0.39
    '),
    0.39
     shop
    0.39
    estamps
    0.39
    --;
    0.38
     使い
    0.38
    POSITIVE LOGITS
    Bathroom
    0.56
    妘
    0.48
     musicales
    0.46
    atuan
    0.46
    Église
    0.45
    Basketball
    0.45
    का
    0.45
    ங்கோ
    0.45
    Rab
    0.44
    อต
    0.44
    Activations Density 0.001%

    No Known Activations