© 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. 14809
    Prev
    Next
    INDEX
    Explanations

    preparation time

    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
    ipedi
    0.55
    ចាប់
    0.55
    블
    0.55
    カテゴリ
    0.54
     পরম
    0.53
    Alberto
    0.52
    pena
    0.52
    bla
    0.52
    ownika
    0.51
    vori
    0.50
    POSITIVE LOGITS
     societal
    0.54
     societ
    0.51
     portal
    0.50
     акций
    0.49
    蟾
    0.49
    bury
    0.48
     Burgh
    0.48
     karma
    0.47
     اگ
    0.47
     partito
    0.47
    Activations Density 0.013%

    No Known Activations