© 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. 195244
    Prev
    Next
    INDEX
    Explanations

    build

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

    motivations, connections, and influence

    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
    जा
    0.51
     MIR
    0.51
     ahí
    0.50
    İN
    0.50
     MRI
    0.49
    ք
    0.49
     dica
    0.48
    ஜன்
    0.48
     MOQ
    0.47
    ய
    0.47
    POSITIVE LOGITS
    march
    0.49
    addSprite
    0.49
    anakk
    0.47
    𒁺
    0.46
    matic
    0.45
    fds
    0.45
    atthakath
    0.44
    ស្រាយ
    0.44
    ছিল
    0.44
    літы
    0.43
    Activations Density 0.000%

    No Known Activations