© 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. 55947
    Prev
    Next
    INDEX
    Explanations

    appropriate safeguards

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

    problems and issues

    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
     zoo
    0.57
    zoo
    0.52
     ―
    0.51
     Zoo
    0.49
     coût
    0.49
     dowol
    0.49
     slanted
    0.48
     planner
    0.48
     Хоккей
    0.47
     calc
    0.47
    POSITIVE LOGITS
     Vestone
    0.58
    т
    0.52
    eder
    0.49
    гна
    0.48
    бен
    0.47
    endosi
    0.47
    eban
    0.46
    οντας
    0.46
    dimensionality
    0.46
    ankan
    0.46
    Activations Density 0.000%

    No Known Activations