© 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. 15741
    Prev
    Next
    INDEX
    Explanations

    support

    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
    োনাম
    0.47
    astan
    0.46
    啐
    0.46
    क्लेव
    0.45
    ორე
    0.45
    izhou
    0.44
    acrylamide
    0.43
    jaer
    0.43
    呔
    0.42
    риз
    0.41
    POSITIVE LOGITS
     support
    5.44
     Support
    5.25
     SUPPORT
    5.16
    support
    5.13
    Support
    5.13
    支持
    5.00
    SUPPORT
    4.78
    サポート
    4.75
     suport
    4.75
     supports
    4.72
    Activations Density 0.468%

    No Known Activations