© 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. 128302
    Prev
    Next
    INDEX
    Explanations

    programming config

    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
     we
    -2.88
    
    -2.81
    …(
    -2.72
    or
    -2.69
    that
    -2.64
    ..(
    -2.59
    ྵ
    -2.55
    眎
    -2.52
    and
    -2.47
    ,;
    -2.41
    POSITIVE LOGITS
    でございます
    2.98
    ୈ
    2.81
     歳
    2.81
    しちゃ
    2.78
    〜。
    2.52
    ITCHEN
    2.50
    的问
    2.44
    筝
    2.44
    ﹔
    2.42
    皚
    2.42
    Activations Density 0.010%

    No Known Activations