© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 26643
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical questions

    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_22/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
    lelő
    -1.12
     its
    -1.04
    itás
    -1.02
    inawa
    -1.00
     abgerufen
    -1.00
     muualla
    -1.00
     altura
    -0.99
     heights
    -0.98
    此人
    -0.97
    ようになりました
    -0.96
    POSITIVE LOGITS
    <bos>
    1.20
    Ingredi
    1.17
    راسیون
    1.14
    があり
    1.13
    がありますが
    1.09
    があります
    1.09
    Sehr
    1.09
    kepada
    1.05
     могут
    1.05
    と思われます
    1.05
    Activations Density 0.000%

    No Known Activations