© 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. 148483
    Prev
    Next
    INDEX
    Explanations

    specialized verbs and nouns

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

    risk or imaginary concepts

    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
    왈
    0.47
    icultural
    0.46
    엊
    0.45
    喈
    0.45
    쇤
    0.45
    єте
    0.44
    ⏱
    0.44
    ここは
    0.44
    榈
    0.43
    ії
    0.43
    POSITIVE LOGITS
    aas
    0.52
     conocidos
    0.44
    bamos
    0.42
    lua
    0.42
    tais
    0.42
     aas
    0.42
    坐
    0.41
     կ
    0.40
    ম্বা
    0.40
     bekannt
    0.40
    Activations Density 0.000%

    No Known Activations