© 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. 15208
    Prev
    Next
    INDEX
    Explanations

    unity

    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
    rahman
    0.65
    mathbf
    0.64
     !}
    0.57
    ziem
    0.57
    >}
    0.55
     бў
    0.54
     الكريم
    0.54
    ôr
    0.54
    rograman
    0.54
    istischen
    0.54
    POSITIVE LOGITS
    Unity
    0.56
    unity
    0.53
    诬
    0.52
     Unity
    0.52
    ????
    0.50
    눗
    0.50
    ?.
    0.50
     vok
    0.50
    如
    0.50
    ?????
    0.49
    Activations Density 0.000%

    No Known Activations