© 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. 13602
    Prev
    Next
    INDEX
    Explanations

    evaluation assessment

    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
     бесплатно
    0.55
     dunno
    0.55
    ፨
    0.55
    Go
    0.54
    ござい
    0.54
    GO
    0.54
     Gover
    0.53
    បត្តិ
    0.53
    دیای
    0.53
    悄
    0.53
    POSITIVE LOGITS
     rating
    0.83
     ratings
    0.81
     assessment
    0.78
     assessments
    0.68
     रेटिंग
    0.68
     оценки
    0.67
     Ratings
    0.66
     appraisal
    0.65
     inspection
    0.64
     evaluation
    0.64
    Activations Density 0.000%

    No Known Activations