© 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. 15195
    Prev
    Next
    INDEX
    Explanations

    potential customers

    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
    眷
    0.52
     Kast
    0.48
    伖
    0.48
     स्किप
    0.48
    中毒
    0.46
     Fragmentation
    0.46
     mati
    0.45
    芴
    0.44
     تغ
    0.44
     debris
    0.44
    POSITIVE LOGITS
     potential
    3.72
     prospective
    3.72
    potential
    3.63
    Potential
    3.59
     Potential
    3.56
     потенциа
    3.44
     Prospective
    3.44
     potencial
    3.09
     potenciales
    3.08
    pros
    3.03
    Activations Density 0.232%

    No Known Activations