© 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. 39720
    Prev
    Next
    INDEX
    Explanations

    weekend calls

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

    . This. Issues. two. physicallyare twoare specific

    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
    tw
    0.53
    ann
    0.50
    各
    0.50
    dat
    0.49
    good
    0.49
    lots
    0.49
    when
    0.48
    p
    0.48
    ’
    0.48
    isbn
    0.47
    POSITIVE LOGITS
     camas
    0.56
     barren
    0.52
     કા
    0.49
     unreachable
    0.49
     Ла
    0.48
     distante
    0.47
     verduras
    0.47
     devast
    0.47
     дъ
    0.47
     Mä
    0.46
    Activations Density 0.000%

    No Known Activations