© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68529
    Prev
    Next
    INDEX
    Explanations

    code ending in parentheses or semicolon

    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
    一切
    -1.34
    にします
    -1.14
    あー
    -1.14
    来週
    -1.13
    つづく
    -1.13
    いえ
    -1.09
     davvero
    -1.07
     cinturón
    -1.05
    際に
    -1.04
    citroen
    -1.04
    POSITIVE LOGITS
    <bos>
    1.12
     '+':
    1.11
    内容は
    1.09
    ziehungs
    1.05
    UserScript
    1.04
     '/';
    1.02
    ajú
    0.99
    開花
    0.98
    plätze
    0.98
    けれど
    0.98
    Activations Density 0.007%

    No Known Activations