© 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. 3815
    Prev
    Next
    INDEX
    Explanations

    file sizes and compression reduction

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

    code, comments, and punctuation

    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
     INKA
    0.46
    Colonne
    0.45
    様子
    0.41
    \|=\
    0.41
    Mountains
    0.40
    IRCON
    0.40
    STIT
    0.40
     ಒಂದು
    0.39
    ृता
    0.39
    QUE
    0.39
    POSITIVE LOGITS
    optimize
    0.40
    层次
    0.39
    虽然
    0.38
     although
    0.38
    ian
    0.37
     honed
    0.37
     paranoid
    0.37
     stressing
    0.36
     ™
    0.36
    正则表达式
    0.36
    Activations Density 0.004%

    No Known Activations