© 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. 176739
    Prev
    Next
    INDEX
    Explanations

    contestant, Rider, employee

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

    list terminators or function separators

    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
     }}^{\
    0.44
    <0xE2>
    0.43
    ಗೆ
    0.40
    エイ
    0.39
    ve
    0.38
    wia
    0.38
    vd
    0.38
    Ln
    0.38
    ]))
    0.38
     部
    0.38
    POSITIVE LOGITS
     Boiling
    0.54
     boiling
    0.52
     कोणत्याही
    0.50
    наў
    0.48
     conservatory
    0.48
    োহণ
    0.47
     همین
    0.46
    ternut
    0.46
     posicao
    0.46
    ㇁
    0.46
    Activations Density 0.001%

    No Known Activations