© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 136129
    Prev
    Next
    INDEX
    Explanations

    procedures and explanation

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

    a bit

    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
     mancan
    0.59
    まります
    0.49
    湯
    0.48
     dô
    0.47
     こう
    0.47
     concom
    0.47
    🚲
    0.46
     причинам
    0.45
     temprana
    0.45
     crescere
    0.45
    POSITIVE LOGITS
    s
    0.55
    an
    0.51
    ins
    0.49
     Federation
    0.49
    ys
    0.48
    ids
    0.47
    clave
    0.47
    as
    0.46
    aders
    0.46
     Panel
    0.46
    Activations Density 0.000%

    No Known Activations