© 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. 27140
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    ビックリ
    -0.88
    optionalTypeArgs
    -0.87
    づけ
    -0.85
    kennen
    -0.84
     tient
    -0.84
    唖
    -0.84
    балан
    -0.84
     luminoso
    -0.84
     cette
    -0.83
     florales
    -0.82
    POSITIVE LOGITS
    Sa
    0.94
    -
    0.92
     to
    0.91
    Ahol
    0.84
    Che
    0.84
    Yes
    0.83
     erwähnten
    0.82
    Still
    0.82
     fuera
    0.81
    radura
    0.79
    Activations Density 0.070%

    No Known Activations