© 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. 39368
    Prev
    Next
    INDEX
    Explanations

    definitions and code snippets

    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
    érard
    0.49
    zug
    0.46
    াউন
    0.44
    intérieur
    0.43
    jährigen
    0.42
    𝗳
    0.42
    ynku
    0.40
    jiv
    0.40
    SourceObject
    0.40
    煖
    0.39
    POSITIVE LOGITS
    ,:
    0.46
    ,’
    0.43
    ’,
    0.42
     permit
    0.40
    ’),
    0.39
    ’)
    0.39
     procede
    0.38
    DNS
    0.37
    вшей
    0.37
    HLA
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.