© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71257
    Prev
    Next
    INDEX
    Explanations

    _ token completion

    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_10/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
     our
    -1.86
     We
    -1.66
     avevo
    -1.63
    這種
    -1.60
     concluir
    -1.59
     convencer
    -1.59
    ⅾ
    -1.59
     transmitir
    -1.55
    ꜰ
    -1.55
     provocar
    -1.54
    POSITIVE LOGITS
     \
    1.68
     «
    1.64
    presented
    1.61
    DebuggerStep
    1.57
     —
    1.57
    
    1.56
     \&
    1.56
    但在
    1.53
    ”
    1.52
     “
    1.52
    Activations Density 0.042%

    No Known Activations