© 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. 136146
    Prev
    Next
    INDEX
    Explanations

    about protection or related concepts

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

    found dead

    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
     গুজ
    0.50
    itochond
    0.49
    セル
    0.47
    utches
    0.47
    ambuco
    0.47
    hitth
    0.46
     اللہ
    0.46
    }{
    0.45
    uffle
    0.45
    rike
    0.45
    POSITIVE LOGITS
     despre
    0.53
     terão
    0.52
     proteção
    0.50
     hakkında
    0.48
    боли
    0.48
     terá
    0.47
     clears
    0.47
     esfor
    0.47
    a
    0.46
     protección
    0.45
    Activations Density 0.001%

    No Known Activations