© 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. 65663
    Prev
    Next
    INDEX
    Explanations

    helping with a service or role

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

    CPU, strike, presentation, causes, metá, things, source, targets

    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
    North
    0.49
    north
    0.46
     buoyant
    0.46
    tries
    0.46
    u
    0.46
    lVert
    0.45
    mouth
    0.45
     accidentally
    0.45
    opponent
    0.44
     North
    0.44
    POSITIVE LOGITS
    斟
    0.42
    దా
    0.41
     ادارے
    0.41
    とその
    0.40
    Cuánto
    0.38
    ordon
    0.38
    껏
    0.38
     МО
    0.37
    ورو
    0.37
     pouquinho
    0.36
    Activations Density 0.000%

    No Known Activations