© 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. 65885
    Prev
    Next
    INDEX
    Explanations

    formatting around data

    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
     potranno
    -1.02
    Namun
    -0.92
     sentirse
    -0.90
     relaj
    -0.90
     Vân
    -0.89
    ſing
    -0.88
    SUNG
    -0.86
    openg
    -0.86
    бина
    -0.85
     siapa
    -0.85
    POSITIVE LOGITS
    験
    0.93
     bacilli
    0.90
    悟
    0.88
     αρχ
    0.87
    扭曲
    0.84
     дела
    0.84
     tatsäch
    0.83
     one
    0.82
    一条
    0.82
    ‌است
    0.82
    Activations Density 0.099%

    No Known Activations