© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41103
    Prev
    Next
    INDEX
    Explanations

    by introducing methods

    np_acts-logits-general · gemini-2.5-flash-lite

    methods or processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ≈
    0.49
     CPUs
    0.47
    :
    0.47
     datasets
    0.47
     输出
    0.46
    metrics
    0.44
    datasets
    0.44
     univariate
    0.43
     {
    0.42
     $\
    0.42
    POSITIVE LOGITS
     ajust
    0.44
    കൂ
    0.44
     मथुरा
    0.44
    immen
    0.44
    उंट
    0.43
    orest
    0.43
     richtig
    0.42
    órico
    0.42
     prit
    0.41
    كر
    0.41
    Activations Density 0.005%

    No Known Activations