© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 187217
    Prev
    Next
    INDEX
    Explanations

    red Levi's store evaluate

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

    strong modifiers and actions

    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
    Negative Logits
     geleden
    0.42
    肉
    0.41
    LVector
    0.41
     tomada
    0.41
    لين
    0.41
    ျေး
    0.41
    ljed
    0.41
     {
    0.40
     thơ
    0.40
    apellido
    0.40
    POSITIVE LOGITS
     At
    0.52
    й
    0.52
    smanship
    0.52
    )
    0.51
     страхо
    0.50
    ).
    0.50
    י
    0.48
    สต
    0.48
    UnderWater
    0.47
     Makes
    0.46
    Activations Density 0.001%

    No Known Activations