© 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. 79140
    Prev
    Next
    INDEX
    Explanations

    good shepherd

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

    code, release, text

    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
    altungen
    0.41
    को
    0.41
    niej
    0.40
    ститу
    0.40
    ichtung
    0.40
    otification
    0.40
    晰
    0.40
     невро
    0.39
    bentuk
    0.38
     सपनों
    0.38
    POSITIVE LOGITS
    ╲
    0.44
     shop
    0.42
    SHOP
    0.41
     fair
    0.41
    unin
    0.40
     active
    0.40
    arela
    0.39
     Cair
    0.39
     invest
    0.39
     backcountry
    0.39
    Activations Density 0.000%

    No Known Activations