© 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. 133719
    Prev
    Next
    INDEX
    Explanations

    hand until, steal cheetah

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

    related to numbers, specific terms, or punctuation

    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
     Daar
    0.49
    ukuran
    0.48
     ਰ
    0.47
     مدت
    0.47
     rencana
    0.47
     প্রতিক্রিয়া
    0.47
    اون
    0.47
     bekas
    0.46
    jedno
    0.46
    ciencia
    0.45
    POSITIVE LOGITS
     {
    0.48
    (){
    0.48
    숟
    0.47
    (\
    0.47
    觑
    0.46
     cumbersome
    0.46
     scorer
    0.46
     covariate
    0.46
    ());
    0.46
    Tagged
    0.46
    Activations Density 0.001%

    No Known Activations