© 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. 13028
    Prev
    Next
    INDEX
    Explanations

    =

    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
    ্বক
    0.68
    ｹ
    0.68
    льнявыя
    0.67
     Recordemos
    0.65
     Roanoke
    0.65
     Eurostile
    0.65
     cohom
    0.64
     invariable
    0.64
     maqu
    0.64
     coseno
    0.64
    POSITIVE LOGITS
     {{
    0.73
    {{
    0.70
    NonNull
    0.60
    set
    0.60
    f
    0.59
     "{{
    0.58
    en
    0.58
     {
    0.57
    ="
    0.57
    UTF
    0.57
    Activations Density 0.000%

    No Known Activations