© 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. 10-GEMMASCOPE-RES-131K
    7. 21350
    Prev
    Next
    INDEX
    Explanations

    ip addresses

    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
     —
    -3.55
    <em>
    -3.45
    an
    -3.42
     –
    -3.39
    .
    -3.30
     were
    -3.11
    It
    -2.97
     of
    -2.92
     have
    -2.77
    0
    -2.64
    POSITIVE LOGITS
    
    2.97
     was
    2.94
    Leírás
    2.77
    𝄆
    2.63
    샅
    2.61
     parfüm
    2.58
     has
    2.55
    ꯷
    2.55
    锃
    2.50
    懌
    2.50
    Activations Density 0.014%

    No Known Activations