© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6978
    Prev
    Next
    INDEX
    Explanations

    this, that, these

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     luisant
    0.59
     classify
    0.57
    XmlApplication
    0.56
     पेड
    0.56
     প্রশংসা
    0.55
    ভ
    0.55
     टकरा
    0.54
    愜
    0.54
     рыб
    0.53
    Genres
    0.52
    POSITIVE LOGITS
    อส
    0.53
    regar
    0.52
     supremum
    0.52
     Ев
    0.52
    廨
    0.52
     တယ်
    0.50
    维度
    0.49
    တယ်။
    0.48
     mediast
    0.48
    enos
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.