© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15224
    Prev
    Next
    INDEX
    Explanations

    auxiliary have

    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
     Aqui
    0.64
     HSA
    0.59
    Aqui
    0.59
     Auf
    0.56
     façons
    0.56
     hafa
    0.56
     Até
    0.55
    艐
    0.55
    okines
    0.55
     feas
    0.54
    POSITIVE LOGITS
    აში
    0.67
     multiple
    0.63
    multiple
    0.63
    Multiple
    0.59
     two
    0.58
    是
    0.58
     आहे
    0.57
    Scale
    0.57
     Multiple
    0.57
    两个
    0.56
    Activations Density 0.008%

    No Known Activations