© 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. 31120
    Prev
    Next
    INDEX
    Explanations

    as per

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

    predetermined, recapture, back cover, clamp

    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
    谲
    0.58
    鐒
    0.58
     정의역
    0.52
     médec
    0.50
     Héctor
    0.49
     Евге
    0.49
     ugljik
    0.49
     Türkei
    0.48
     Ичиго
    0.47
     arrondies
    0.47
    POSITIVE LOGITS
    ’
    0.65
    long
    0.50
     power
    0.50
    lin
    0.49
    iqu
    0.47
    world
    0.47
    begin
    0.46
     recently
    0.46
     l
    0.46
    lish
    0.45
    Activations Density 0.000%

    No Known Activations