© 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. 13324
    Prev
    Next
    INDEX
    Explanations

    up

    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
     houve
    0.57
    tschaft
    0.54
    ību
    0.54
     diminishes
    0.52
    年から
    0.52
    ન્સ
    0.51
    𝐾
    0.51
     descripción
    0.50
    ụy
    0.50
    衡
    0.50
    POSITIVE LOGITS
     updated
    0.96
    updated
    0.79
     aktual
    0.75
    Updated
    0.71
     actualizada
    0.71
     Updated
    0.70
    ato
    0.69
    토
    0.68
    To
    0.66
     актуа
    0.66
    Activations Density 0.017%

    No Known Activations