© 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. 126865
    Prev
    Next
    INDEX
    Explanations

    free or seminars or exponents or Sar

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

    code execution related keywords

    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
    მ
    0.54
    utus
    0.49
    ᓱ
    0.49
    тер
    0.49
    жде
    0.48
    штейн
    0.48
    麦
    0.48
    grund
    0.46
    ⧐
    0.46
    unarod
    0.46
    POSITIVE LOGITS
     goalie
    0.59
     unbeaten
    0.54
     fighters
    0.53
     watched
    0.50
     penalty
    0.49
     skaters
    0.49
     hunters
    0.48
     warriors
    0.48
     yells
    0.48
     regrettable
    0.47
    Activations Density 0.000%

    No Known Activations