© 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. 12846
    Prev
    Next
    INDEX
    Explanations

    informal descriptions

    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
    ၍
    0.70
     จึง
    0.70
    ।-
    0.68
    अधिकांश
    0.64
    வ்வேறு
    0.64
     திருதியை
    0.63
     多く
    0.61
     অনুরূপ
    0.61
    ၌
    0.60
     শতাধিক
    0.60
    POSITIVE LOGITS
     yeah
    2.69
     yep
    2.52
     blah
    2.47
     dude
    2.44
     huh
    2.41
     dudes
    2.41
     kinda
    2.39
    yeah
    2.31
     dunno
    2.22
    めっちゃ
    2.22
    Activations Density 0.217%

    No Known Activations