© 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. 63368
    Prev
    Next
    INDEX
    Explanations

    own PC

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

    subverting expectations

    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
    Negative Logits
     Pendidikan
    0.48
     enjeux
    0.46
     moteurs
    0.46
    ᅴ
    0.45
     substantiate
    0.45
    忐
    0.45
     adhé
    0.45
     schrift
    0.44
    ᅵ
    0.44
     trastornos
    0.44
    POSITIVE LOGITS
    AT
    0.50
    ELL
    0.46
    Seal
    0.45
    icator
    0.43
    DOC
    0.42
    С
    0.42
    Combine
    0.42
    ificador
    0.42
    Transaction
    0.41
     Nimbus
    0.41
    Activations Density 0.000%

    No Known Activations