© 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. 14119
    Prev
    Next
    INDEX
    Explanations

    rank

    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
    皿
    0.56
     chag
    0.53
    доз
    0.51
    盅
    0.50
     screws
    0.48
    プレート
    0.48
    ög
    0.48
     chewing
    0.48
    줍
    0.48
    achet
    0.47
    POSITIVE LOGITS
     rank
    5.72
    Rank
    5.41
     ranks
    5.31
     Rank
    5.31
     ranking
    5.28
    rank
    5.25
     RANK
    5.22
     ranked
    5.13
    RANK
    5.06
     Ranking
    4.88
    Activations Density 0.156%

    No Known Activations