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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-262K
    4. 2401
    Prev
    Next
    INDEX
    Explanations

    addressing you directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anew
    0.73
    .
    0.63
    ৮
    0.62
     чтобы
    0.61
     polymorphic
    0.61
    ".
    0.60
     itself
    0.59
    ³
    0.58
    ۔
    0.57
     diarrhoea
    0.57
    POSITIVE LOGITS
    re
    0.85
    inicio
    0.78
    ve
    0.77
    रे
    0.77
    cc
    0.73
     Yourself
    0.72
    utilizzo
    0.71
    झ्
    0.71
     Lordships
    0.70
    hn
    0.70
    Activations Density 0.083%

    No Known Activations