© 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. 13083
    Prev
    Next
    INDEX
    Explanations

    consisting of

    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
    埛
    0.50
     kapcs
    0.48
     Qxa
    0.47
     বার্তা
    0.47
    に関連
    0.47
    వాత
    0.46
    szág
    0.46
    䡊
    0.46
    চূ
    0.46
    競争
    0.45
    POSITIVE LOGITS
     consisting
    5.00
     consisted
    4.69
     consists
    4.56
     consist
    4.53
     comprised
    4.44
     composed
    4.28
     terdiri
    4.16
    composed
    3.95
     comprising
    3.88
     består
    3.80
    Activations Density 0.242%

    No Known Activations