© 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. 158307
    Prev
    Next
    INDEX
    Explanations

    relation betweencustom-madebranch historyjust heardeighty percentDianetics session

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

    marketed as, resulting number, this is

    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
    so
    0.52
    bits
    0.49
    kel
    0.48
    jor
    0.48
    ks
    0.47
    郵
    0.46
    mix
    0.46
    dn
    0.45
    gn
    0.45
    ars
    0.45
    POSITIVE LOGITS
     یکی
    0.53
     afbeelding
    0.53
    ToDO
    0.52
     nouvel
    0.51
     변화
    0.50
     изображение
    0.50
    новый
    0.50
     ወ
    0.50
    䍧
    0.50
     የወ
    0.49
    Activations Density 0.000%

    No Known Activations