© 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. 8315
    Prev
    Next
    INDEX
    Explanations

    phrases starting with punctuation or words like 'of', 'for'

    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
     Advisors
    0.61
     Outfitters
    0.61
    <unused1129>
    0.61
     점점
    0.59
     বেশির
    0.59
     empezó
    0.58
     året
    0.58
     곳
    0.57
     Airlines
    0.55
     áreas
    0.55
    POSITIVE LOGITS
     nontrivial
    0.62
    text
    0.61
    double
    0.61
     nausea
    0.60
     double
    0.60
     bijective
    0.58
     hyperbolic
    0.57
    を用いた
    0.57
     stepwise
    0.57
     perturbation
    0.56
    Activations Density 0.001%

    No Known Activations