© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69438
    Prev
    Next
    INDEX
    Explanations

    @param or @return

    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
     作り方
    -1.80
     étrange
    -1.75
     historien
    -1.73
     maji
    -1.73
     豆腐
    -1.70
    canActivate
    -1.69
     nini
    -1.68
     kupa
    -1.66
    ♪♪
    -1.66
     nime
    -1.65
    POSITIVE LOGITS
    ↵
    2.36
     or
    2.30
     other
    2.17
     was
    2.02
     used
    1.91
     It
    1.73
     suoi
    1.70
     knew
    1.69
     do
    1.68
     would
    1.65
    Activations Density 0.018%

    No Known Activations