© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72299
    Prev
    Next
    INDEX
    Explanations

    various syntax structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dê
    -0.88
     Nguy
    -0.88
    фициаль
    -0.85
    {'
    -0.83
    ≅
    -0.82
     ἀ
    -0.82
     時計
    -0.80
     Ν
    -0.79
     expecting
    -0.79
    ディダス
    -0.79
    POSITIVE LOGITS
    ZIONI
    0.95
     time
    0.93
     with
    0.88
    ’，
    0.85
     prudent
    0.85
     two
    0.84
     prøve
    0.83
     five
    0.83
     detailed
    0.81
    ”，
    0.81
    Activations Density 0.000%

    No Known Activations