© 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. 119972
    Prev
    Next
    INDEX
    Explanations

    my, latest, starting point

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

    run by, testing, lack of, Greyhound bus

    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
    Kor
    0.57
    s
    0.54
    ন
    0.53
    Late
    0.50
    ب
    0.48
    प
    0.46
    Depend
    0.45
    Management
    0.45
    ↵
    0.44
    <0x0D>
    0.44
    POSITIVE LOGITS
    ahooks
    0.56
     područ
    0.50
    isan
    0.49
    iful
    0.48
     جیس
    0.47
    ająca
    0.47
    ouncy
    0.47
    formulario
    0.46
    isian
    0.46
    दर्शिता
    0.46
    Activations Density 0.000%

    No Known Activations