© 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. 252061
    Prev
    Next
    INDEX
    Explanations

    waiver, survive, printed, concede

    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
     Tensor
    0.61
     Wirkung
    0.52
     milites
    0.49
     Kanal
    0.48
     Effekt
    0.48
     무
    0.48
     Zy
    0.46
     효과
    0.46
     Respuesta
    0.46
     Erste
    0.46
    POSITIVE LOGITS
    apeake
    0.46
    ষুধ
    0.46
     ਜਾਣ
    0.44
    ্স
    0.44
    らしく
    0.44
    ଷ
    0.44
    вча
    0.43
    perp
    0.43
     ഭക്ഷ
    0.43
    नु
    0.43
    Activations Density 0.001%

    No Known Activations