© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 7062
    Prev
    Next
    INDEX
    Explanations

    password, lock, UI, model, weights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ときに
    0.52
     permitem
    0.50
     permiten
    0.49
    就可以了
    0.49
     により
    0.48
     बचाता
    0.48
    '$.
    0.46
     avulla
    0.46
    allows
    0.46
    .=
    0.46
    POSITIVE LOGITS
     resides
    0.71
     exists
    0.66
     находится
    0.65
     happens
    0.59
     will
    0.57
     belongs
    0.56
     existed
    0.56
     נמצא
    0.56
     has
    0.55
     is
    0.55
    Activations Density 0.002%

    No Known Activations