© 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. 127473
    Prev
    Next
    INDEX
    Explanations

    daily headlines

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

    access and sales strategies

    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
     globales
    0.48
    圄
    0.47
     প্রাস
    0.47
     europe
    0.46
    嫔
    0.46
    ዎቹ
    0.46
     penge
    0.46
     wykon
    0.46
     globale
    0.46
     ostatnich
    0.46
    POSITIVE LOGITS
    ul
    0.45
    ulman
    0.43
    asthenia
    0.43
    ala
    0.43
    alin
    0.43
    izi
    0.42
    ì
    0.42
    estring
    0.40
    le
    0.39
    loglevel
    0.39
    Activations Density 0.000%

    No Known Activations