© 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-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 819
    Prev
    Next
    INDEX
    Explanations

    aspects, factors, features, steps

    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
     a
    0.47
     an
    0.39
    0
    0.38
     the
    0.37
     any
    0.34
    2
    0.33
    5
    0.30
    4
    0.30
    1
    0.30
    -
    0.30
    POSITIVE LOGITS
     aspects
    0.38
     uključ
    0.38
     meliputi
    0.38
     包括
    0.37
     включают
    0.37
     facets
    0.35
    包括
    0.34
     centering
    0.34
    氬
    0.33
    ઃ
    0.33
    Activations Density 0.079%

    No Known Activations