© 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. 41-GEMMASCOPE-2-RES-65K
    7. 13586
    Prev
    Next
    INDEX
    Explanations

    scientific technical terms

    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
    alam
    0.66
    Art
    0.63
    Players
    0.63
    Alam
    0.61
     players
    0.60
     Alam
    0.60
    Jo
    0.59
    W
    0.59
     Players
    0.58
    ed
    0.57
    POSITIVE LOGITS
     möchten
    0.63
     подска
    0.61
     hysteresis
    0.59
     melanjutkan
    0.59
    ׃
    0.59
     lös
    0.57
     kêu
    0.57
     ใ
    0.56
     androgen
    0.56
     hydrating
    0.56
    Activations Density 0.000%

    No Known Activations