© 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. 15184
    Prev
    Next
    INDEX
    Explanations

    mark

    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
     কাছাকাছি
    0.64
    asey
    0.62
     নিকটে
    0.59
    enf
    0.59
     وهكذا
    0.59
     Э
    0.56
    િતિ
    0.55
     случаев
    0.55
    ianas
    0.54
    elya
    0.54
    POSITIVE LOGITS
     MARK
    0.64
    Mark
    0.60
    ̉i
    0.60
    Marks
    0.59
    .}(
    0.57
    }{
    0.57
    MARK
    0.55
    )()
    0.55
     Marks
    0.54
    }}}{
    0.54
    Activations Density 0.000%

    No Known Activations