© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60695
    Prev
    Next
    INDEX
    Explanations

    attribute accessors

    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
    髫
    -1.81
     toalla
    -1.76
    、
    -1.64
    🪜
    -1.63
     geldi
    -1.61
    ፳
    -1.57
     början
    -1.55
     étan
    -1.55
     belki
    -1.52
     lää
    -1.51
    POSITIVE LOGITS
    )
    2.27
    .
    2.11
    There
    1.87
    It
    1.84
    Since
    1.82
    In
    1.80
    So
    1.80
     are
    1.78
    8
    1.76
     in
    1.75
    Activations Density 0.000%

    No Known Activations