Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-262K
    4. 240938
    Prev
    Next
    INDEX
    Explanations

    Wakanda

    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
    風
    0.56
    ля
    0.54
     Rear
    0.52
    edas
    0.52
    建成
    0.51
     Specifically
    0.49
     Registry
    0.49
    Rear
    0.49
     ወ
    0.48
     Graves
    0.48
    POSITIVE LOGITS
     wak
    0.74
    Wak
    0.73
    wak
    0.61
     अध्यक्ष
    0.59
     Wak
    0.58
     त्या
    0.54
     richness
    0.54
    alat
    0.52
     dieren
    0.52
    acje
    0.51
    Activations Density 0.003%

    No Known Activations