© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 225104
    Prev
    Next
    INDEX
    Explanations

    Men movies, decade had, oxidizing is, addressing the

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

    negative or challenging situations

    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
     $("<
    0.45
     teaches
    0.45
     দেখি
    0.45
    getPath
    0.44
     ao
    0.44
     suspect
    0.43
     ويت
    0.43
    ୍କ
    0.42
     shakes
    0.42
    ේෂ
    0.42
    POSITIVE LOGITS
    im
    0.63
    bromide
    0.52
    ه
    0.52
    a
    0.51
    па
    0.49
    uene
    0.48
     Abol
    0.47
    лил
    0.47
    बंदी
    0.47
    em
    0.46
    Activations Density 0.000%

    No Known Activations