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. 241137
    Prev
    Next
    INDEX
    Explanations

    research and obtained

    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
    rosine
    0.62
     selam
    0.57
     पुढ
    0.52
    ته
    0.51
    リーム
    0.49
     vaš
    0.48
     яс
    0.48
    ὺ
    0.48
     lordship
    0.47
    ριά
    0.47
    POSITIVE LOGITS
     Obtained
    0.66
    hypoth
    0.64
     Toler
    0.62
     obtained
    0.60
    cement
    0.60
    疙
    0.59
     നില
    0.59
    obt
    0.57
     runt
    0.57
    repeated
    0.57
    Activations Density 0.000%

    No Known Activations