© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13896
    Prev
    Next
    INDEX
    Explanations

    say "available"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    ത്തിലാണ്
    0.55
     স্বায়
    0.46
    巍
    0.46
    تمي
    0.46
    綎
    0.46
    кономі
    0.45
    ieu
    0.45
    രാണ്
    0.45
    ற்கான
    0.45
    殲
    0.44
    POSITIVE LOGITS
     available
    5.72
    available
    5.50
    Available
    5.38
     Available
    5.31
     disponible
    5.09
     disponibles
    5.00
     AVAILABLE
    4.91
     disponível
    4.81
     disponibile
    4.75
     disponíveis
    4.75
    Activations Density 0.631%

    No Known Activations