© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127775
    Prev
    Next
    INDEX
    Explanations

    task, traits, keys, manipulative therapy, license

    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/layer_31_width_262k_l0_medium
    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
    Contain
    0.50
    Chúng
    0.50
     জ্বল
    0.48
     อ
    0.48
    Fire
    0.47
     พวก
    0.47
     органы
    0.47
     оружия
    0.46
     күз
    0.46
    Catagory
    0.46
    POSITIVE LOGITS
     protracted
    0.40
     precies
    0.39
     odnosno
    0.38
    liminf
    0.38
    -
    0.38
     renegoti
    0.38
     precisely
    0.38
    aa
    0.37
     skorzyst
    0.37
    ῇ
    0.37
    Activations Density 0.009%

    No Known Activations