© 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-262K
    7. 241447
    Prev
    Next
    INDEX
    Explanations

    offerings or services

    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_262k_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
     সবাই
    0.64
    Ṣ
    0.62
    descriptor
    0.60
    INR
    0.58
     酒
    0.57
    Sà
    0.57
    прочем
    0.56
    所有人
    0.55
    languageTag
    0.54
    酒
    0.54
    POSITIVE LOGITS
     prenatal
    0.59
     મળ
    0.58
     Tirol
    0.57
     Genome
    0.56
     agricultural
    0.54
     ecological
    0.54
     eco
    0.54
     medicine
    0.54
    itters
    0.54
    ibus
    0.53
    Activations Density 0.002%

    No Known Activations