© 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. 33145
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

    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
     in
    -1.11
     with
    -1.02
     ใหม่
    -1.02
     to
    -1.01
    DataTo
    -0.91
     even
    -0.90
    ர்
    -0.89
    ਆ
    -0.89
     which
    -0.89
    êtres
    -0.87
    POSITIVE LOGITS
    iosos
    1.07
    าหล
    1.05
     limitaciones
    1.02
    勠
    1.02
     ـ
    0.98
    rodek
    0.97
     државе
    0.96
     няколко
    0.95
    嘹
    0.95
     concent
    0.93
    Activations Density 0.004%

    No Known Activations