© 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. 14271
    Prev
    Next
    INDEX
    Explanations

    ism

    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
     raiſ
    -2.73
    緜
    -2.59
     opérés
    -2.52
     広場
    -2.50
     uſed
    -2.45
     described
    -2.42
     become
    -2.41
    的吗
    -2.39
     referenced
    -2.38
    敍
    -2.38
    POSITIVE LOGITS
    ism
    2.64
    蠖
    2.64
     "
    2.59
    {
    2.58
    珵
    2.50
     pregunt
    2.42
    </sup>
    2.41
    ↵↵↵↵↵↵↵↵↵↵↵
    2.33
     It
    2.30
    </b>
    2.27
    Activations Density 0.013%

    No Known Activations