© 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. 41279
    Prev
    Next
    INDEX
    Explanations

    academic scholar professor engineer author

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

    intellectual pursuits and knowledge

    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
     frontend
    0.43
     の
    0.41
     extended
    0.39
     FIG
    0.39
     justified
    0.39
     по
    0.39
     ft
    0.39
    ノ
    0.39
    ンド
    0.38
     Ио
    0.38
    POSITIVE LOGITS
     विद्व
    0.57
     ciencia
    0.54
     مسلمانوں
    0.53
     scienze
    0.53
     scientifique
    0.51
     mennesker
    0.50
    scientists
    0.50
     scientifiques
    0.50
     intelekt
    0.48
    scientist
    0.48
    Activations Density 0.002%

    No Known Activations