© 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. 100557
    Prev
    Next
    INDEX
    Explanations

    the following

    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
     and
    -2.55
     should
    -1.54
     mereka
    -1.48
     znaczy
    -1.41
    Več
    -1.38
     would
    -1.38
    économ
    -1.36
    ֳ
    -1.32
    例
    -1.31
     maceta
    -1.30
    POSITIVE LOGITS
     a
    1.95
    唯一的
    1.54
     peculiar
    1.52
     that
    1.47
    あんまり
    1.40
    面白かった
    1.38
    ︲
    1.37
    カッコいい
    1.36
     especial
    1.34
     fica
    1.34
    Activations Density 0.110%

    No Known Activations