© 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. 57175
    Prev
    Next
    INDEX
    Explanations

    thou multiplied

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

    languages, dialects, or topics

    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
     foodservice
    0.44
     sedentary
    0.43
    成像
    0.42
     博文
    0.42
     microbiome
    0.41
    似
    0.39
     मौजूदा
    0.39
    BoolVar
    0.38
     digestible
    0.38
    TryParse
    0.38
    POSITIVE LOGITS
     Saltar
    0.50
     Entrance
    0.49
     Except
    0.48
     Abroad
    0.48
     Excellency
    0.47
     Eğitim
    0.47
     Inicial
    0.47
     Praia
    0.47
    Խ
    0.46
     Trabajo
    0.46
    Activations Density 0.000%

    No Known Activations