© 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. 58682
    Prev
    Next
    INDEX
    Explanations

    code delimiters and headers

    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
     been
    -2.41
     specialised
    -2.16
    い
    -2.09
     Mitgliedern
    -2.06
     był
    -2.06
     vivido
    -1.98
    独特
    -1.97
     '
    -1.96
    呦
    -1.92
    :
    -1.87
    POSITIVE LOGITS
    yarakat
    3.14
    薷
    2.66
    袛
    2.56
    沵
    2.52
    龊
    2.52
     apartament
    2.36
    堿
    2.36
    睃
    2.33
    𖥧
    2.30
    锝
    2.25
    Activations Density 0.001%

    No Known Activations