© 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. 223855
    Prev
    Next
    INDEX
    Explanations

    rate and units

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

    largest proportion

    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
     لگانا
    0.54
    鲑
    0.54
     پک
    0.54
    انا
    0.52
    ٹنے
    0.52
    搭载
    0.51
     بہانہ
    0.51
     regole
    0.50
    لاین
    0.49
     پی
    0.49
    POSITIVE LOGITS
    {
    0.53
     vigorous
    0.53
    日本語
    0.51
     indebted
    0.48
    received
    0.48
    English
    0.46
    lecture
    0.45
     fractions
    0.45
     mathematic
    0.44
    История
    0.44
    Activations Density 0.000%

    No Known Activations