© 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. 22-GEMMASCOPE-RES-131K
    7. 73205
    Prev
    Next
    INDEX
    Explanations

    listing or providing examples

    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_22/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
     Similar
    -1.15
    N
    -1.04
    )
    -1.03
    S
    -0.97
    R
    -0.97
     objectMapper
    -0.95
    ższy
    -0.93
    V
    -0.93
    _
    -0.92
     was
    -0.91
    POSITIVE LOGITS
     such
    3.03
     таких
    1.69
    例如
    1.61
    such
    1.59
     مانند
    1.56
     такие
    1.55
     вроде
    1.54
    比如
    1.52
     like
    1.47
     SUCH
    1.47
    Activations Density 0.439%

    No Known Activations