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. 240833
    Prev
    Next
    INDEX
    Explanations

    Sexual

    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
     WIL
    0.63
    त्स
    0.62
    gå
    0.61
    PAAm
    0.61
     immunoglobulin
    0.60
     antibodies
    0.58
     SIX
    0.57
     RE
    0.56
     NAS
    0.56
    jej
    0.56
    POSITIVE LOGITS
    アリ
    0.58
    Iter
    0.54
    াবাদ
    0.54
    ARIA
    0.53
     Washer
    0.53
    EMAN
    0.52
    Cup
    0.52
    Uart
    0.52
    の使い方
    0.52
     уде
    0.51
    Activations Density 0.000%

    No Known Activations