© 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. 112696
    Prev
    Next
    INDEX
    Explanations

    low values

    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
    ﹶ
    -1.83
    んですが
    -1.77
    ྜ
    -1.73
    珦
    -1.68
     tuvimos
    -1.59
    になりますが
    -1.58
     sofern
    -1.56
     öffentliche
    -1.55
    迨
    -1.55
    戆
    -1.52
    POSITIVE LOGITS
    s
    2.34
    です
    1.96
    能
    1.87
    Ꮂ
    1.84
    縢
    1.84
    ográfica
    1.74
    ：「
    1.74
     :}
    1.73
    ченные
    1.68
    也
    1.68
    Activations Density 0.019%

    No Known Activations