© 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. 86072
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     if
    -2.44
    MAXN
    -1.96
    >}
    -1.78
     and
    -1.70
    =}
    -1.60
    〖
    -1.53
    If
    -1.51
    ⚋
    -1.51
    .}(
    -1.50
    ковь
    -1.48
    POSITIVE LOGITS
    pecabe
    1.63
     wußte
    1.50
    2
    1.45
    d
    1.40
    1
    1.38
     that
    1.34
    飛機
    1.30
    n
    1.30
    Viernes
    1.26
    6
    1.23
    Activations Density 0.008%

    No Known Activations