© 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. 109059
    Prev
    Next
    INDEX
    Explanations

    risks, accused, expect

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

    code comments and procedures

    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
    🤽
    0.45
    श्मा
    0.45
     прибыль
    0.44
     filho
    0.44
     कोणत्याही
    0.43
     पालक
    0.43
    枉
    0.43
    ifaiFace
    0.43
     иң
    0.43
    💸
    0.43
    POSITIVE LOGITS
    ناک
    0.60
    Z
    0.57
    v
    0.55
    with
    0.53
    t
    0.51
    d
    0.50
    W
    0.49
    tailed
    0.48
    ok
    0.46
    b
    0.46
    Activations Density 0.000%

    No Known Activations