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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-65K
    4. 231
    Prev
    Next
    INDEX
    Explanations

    predictive modeling and metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     longtime
    1.08
     물
    1.06
     සඳ
    0.98
    +}^{
    0.98
     Ginkuhà
    0.95
    ₂)
    0.94
    滙
    0.94
    __).
    0.94
    复制代码
    0.92
    ಲೆಂ
    0.91
    POSITIVE LOGITS
    ,
    0.96
     for
    0.90
     (
    0.88
     For
    0.85
    :
    0.84
     of
    0.84
     für
    0.83
     predictive
    0.82
     partielle
    0.81
     Predicting
    0.81
    Activations Density 0.000%

    No Known Activations