© 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. 13865
    Prev
    Next
    INDEX
    Explanations

    launch code

    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
     Robo
    0.63
     Sobolev
    0.60
     Contributions
    0.59
     Dependencies
    0.57
    袍
    0.55
    قيم
    0.55
     dependencies
    0.54
     Queue
    0.53
     Rob
    0.52
     Reconstruction
    0.52
    POSITIVE LOGITS
    jdt
    0.63
    launch
    0.59
    魟
    0.57
    durationType
    0.56
     boyunca
    0.55
    俞
    0.55
     launch
    0.54
    ija
    0.54
    Launch
    0.54
    ੁਰ
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.