© 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
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 15298
    Prev
    Next
    INDEX
    Explanations

    Ok

    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
     miš
    0.63
    Renew
    0.55
    newline
    0.54
    ບໍ
    0.51
     गरेको
    0.50
    renew
    0.49
    Раз
    0.48
    迈
    0.47
    indust
    0.46
    PSW
    0.46
    POSITIVE LOGITS
     Corral
    0.77
    asional
    0.75
    tober
    0.70
    ays
    0.67
    okok
    0.66
     corral
    0.66
    繃
    0.64
    AY
    0.64
    azaki
    0.63
    HttpClient
    0.59
    Activations Density 0.041%

    No Known Activations