© 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. 146882
    Prev
    Next
    INDEX
    Explanations

    for victims

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

    language proficiency and capabilities

    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
     spots
    0.54
    མ
    0.53
     cylinder
    0.52
     pockets
    0.51
     cylinders
    0.51
     today
    0.49
     iPod
    0.48
     acetylation
    0.48
     bags
    0.48
     electricity
    0.47
    POSITIVE LOGITS
    getEstado
    0.49
    únior
    0.48
    硏
    0.46
    unehmen
    0.45
    enseit
    0.45
    sendLog
    0.44
    傊
    0.44
    getTime
    0.44
     timid
    0.44
     النفس
    0.44
    Activations Density 0.001%

    No Known Activations