© 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. 71996
    Prev
    Next
    INDEX
    Explanations

    Pyongyang could, this album, organization carry, target companies

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

    list or list item

    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
    -\
    0.51
    uum
    0.50
    år
    0.48
    kli
    0.48
    kN
    0.48
    ugen
    0.47
    []}
    0.46
     böl
    0.45
    uş
    0.45
    ują
    0.44
    POSITIVE LOGITS
    さんと
    0.48
    の場合は
    0.48
    に参加
    0.47
     everytime
    0.47
     comfy
    0.46
     చేసే
    0.45
     thúc
    0.45
    ጠቀ
    0.45
    職
    0.45
     únic
    0.44
    Activations Density 0.001%

    No Known Activations