© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71924
    Prev
    Next
    INDEX
    Explanations

    If I so PHP

    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
     때문에
    -1.01
    khó
    -0.95
     remun
    -0.94
    まずは
    -0.93
     каж
    -0.91
    mige
    -0.91
     provar
    -0.91
    rrer
    -0.90
    ͊
    -0.89
     ext
    -0.89
    POSITIVE LOGITS
    ?
    0.92
    Bonus
    0.89
     esfuerzan
    0.88
    ଶ
    0.88
     enfermos
    0.88
    /
    0.88
     пожалуйста
    0.85
    .
    0.85
    '],$
    0.85
    .,
    0.84
    Activations Density 0.206%

    No Known Activations