© 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. 205359
    Prev
    Next
    INDEX
    Explanations

    risk allocation and consequences

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

    objects, time, method, property, individual, term

    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
    Server
    0.55
    County
    0.49
     County
    0.49
    聯
    0.46
    Ch
    0.45
    River
    0.45
     Server
    0.44
    SERVER
    0.44
    VIP
    0.43
    佈
    0.43
    POSITIVE LOGITS
     だけ
    0.52
     PAINE
    0.51
    arguments
    0.50
    extensions
    0.50
     iniciativas
    0.50
     Najib
    0.50
    rennt
    0.50
     බොහෝ
    0.49
     গেরিলারা
    0.49
    rollerskates
    0.48
    Activations Density 0.000%

    No Known Activations