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. 6245
    Prev
    Next
    INDEX
    Explanations

    information at the end

    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
    又は
    0.75
     Aucun
    0.70
     Atau
    0.70
    または
    0.69
     alebo
    0.68
    λικ
    0.66
    )]{
    0.66
     accessed
    0.66
    }\|^
    0.66
     Zugriff
    0.65
    POSITIVE LOGITS
     parte
    0.74
     timeframe
    0.70
     coolness
    0.69
     portion
    0.65
     aspek
    0.64
     waterway
    0.63
     card
    0.62
     bromide
    0.61
     fissure
    0.61
     inland
    0.60
    Activations Density 0.001%

    No Known Activations