© 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. 241506
    Prev
    Next
    INDEX
    Explanations

    transfer or transmit

    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
     queues
    0.62
     angiogenesis
    0.58
     enqueue
    0.57
    oscopes
    0.57
    chetti
    0.57
    शियों
    0.56
     它
    0.55
     velocità
    0.55
     Absatz
    0.55
     tráfico
    0.55
    POSITIVE LOGITS
     transferred
    0.68
    깊
    0.62
    Transfer
    0.58
    (.
    0.58
    compan
    0.58
     ihrer
    0.57
    their
    0.57
    considered
    0.57
    他們的
    0.57
    他们的
    0.56
    Activations Density 0.000%

    No Known Activations