© 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. 47871
    Prev
    Next
    INDEX
    Explanations

    Driver threads

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

    innovative menu, ecosystem, logging function, leave jobs

    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
     детей
    0.53
     дети
    0.50
     kinderen
    0.49
     animals
    0.48
     inher
    0.47
     образования
    0.46
     ш
    0.45
     животных
    0.45
     children
    0.45
     компетен
    0.44
    POSITIVE LOGITS
    appears
    0.54
    ᱓
    0.50
    물의
    0.49
    βολ
    0.48
    ácio
    0.48
    是因为
    0.48
    ową
    0.48
    ísticas
    0.47
    ဏ်
    0.47
    ⇰
    0.47
    Activations Density 0.000%

    No Known Activations