© 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. 128845
    Prev
    Next
    INDEX
    Explanations

    Realm framework and objects

    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
     fossero
    -2.52
    确实是
    -2.27
    usstsein
    -2.27
    __':
    -2.23
    拶
    -2.22
    
    -2.20
    的吧
    -2.20
    可不是
    -2.11
    紧接着
    -2.11
     欣赏
    -2.09
    POSITIVE LOGITS
    <bos>
    2.83
    S
    2.55
    就
    2.52
    Y
    2.50
    E
    2.48
    O
    2.44
    V
    2.33
    let
    2.31
    未来
    2.23
    C
    2.23
    Activations Density 0.002%

    No Known Activations