© 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. 174656
    Prev
    Next
    INDEX
    Explanations

    lists of words and phrases

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

    goals, missions, and needs

    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
     Félix
    0.51
    冦
    0.49
    জিৎ
    0.46
    يمي
    0.46
     Goh
    0.45
     Ramón
    0.45
     Deane
    0.45
     Chab
    0.45
    ي
    0.44
    煐
    0.44
    POSITIVE LOGITS
    v
    0.57
    evaluate
    0.56
    Cc
    0.53
    Hp
    0.53
    Hz
    0.52
    '}}
    0.50
    ut
    0.50
    lb
    0.49
    voting
    0.49
    ip
    0.49
    Activations Density 0.000%

    No Known Activations