© 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. 70749
    Prev
    Next
    INDEX
    Explanations

    dotted border or redux saga

    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
    諌
    -2.27
    我們
    -2.20
    }$
    -2.17
    踌
    -2.02
     программы
    -2.02
    гово
    -1.95
    tedì
    -1.94
    倖
    -1.93
    曙
    -1.93
     psychotic
    -1.93
    POSITIVE LOGITS
    n
    3.28
    “
    3.11
    r
    2.88
    z
    2.72
     –
    2.66
    که
    2.63
    .!
    2.58
     ‚
    2.50
    ated
    2.47
    v
    2.44
    Activations Density 0.001%

    No Known Activations