© 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. 193162
    Prev
    Next
    INDEX
    Explanations

    lists of features or descriptions

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

    Levels, tone, about, key, here

    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
    SequentialGroup
    0.48
    gebnisse
    0.45
     gerek
    0.44
    絬
    0.43
     leaflet
    0.43
     এঁ
    0.43
    VIR
    0.42
     были
    0.42
     branched
    0.42
     ipad
    0.41
    POSITIVE LOGITS
    ය
    0.52
    तिथि
    0.47
    点头
    0.47
    იმ
    0.47
    नव
    0.46
     Syrians
    0.45
     санк
    0.45
    க்கத்தில்
    0.44
    ysty
    0.44
    חס
    0.44
    Activations Density 0.000%

    No Known Activations