© 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. 10-GEMMASCOPE-RES-131K
    4. 14563
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis followed by 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_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
    鶿
    -3.03
    琲
    -2.61
     deliciously
    -2.53
    𖣔
    -2.48
    ኧ
    -2.36
     créer
    -2.34
    𓁹
    -2.31
     permettant
    -2.27
    辚
    -2.27
    摁
    -2.25
    POSITIVE LOGITS
    ");
    2.88
    ).
    2.84
    ');
    2.59
     because
    2.52
     they
    2.30
    );
    
    2.19
     reconoci
    2.17
     when
    2.16
    ());
    2.11
    .”
    2.09
    Activations Density 0.012%

    No Known Activations