© 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. 66394
    Prev
    Next
    INDEX
    Explanations

    words starting with AN

    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
     แต่
    -3.67
     anhänger
    -2.70
     But
    -2.64
    鹉
    -2.64
    人也
    -2.63
     Bedür
    -2.34
    CÓMO
    -2.34
     If
    -2.34
     popoli
    -2.31
    衚
    -2.30
    POSITIVE LOGITS
    {
    3.16
    <
    2.92
    _
    2.81
    D
    2.44
    ised
    2.44
     здания
    2.42
    </b>
    2.41
     AN
    2.38
    *
    2.36
    </h2>
    2.34
    Activations Density 0.004%

    No Known Activations