© 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. 2715
    Prev
    Next
    INDEX
    Explanations

    describing intensity, quality, or scale

    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
    Button
    0.36
    '
    0.36
     Editar
    0.32
    0
    0.32
    。
    0.32
    Toilet
    0.32
    Cancelled
    0.31
     Button
    0.31
    .
    0.31
    Some
    0.30
    POSITIVE LOGITS
    neſs
    0.41
     provenance
    0.38
     storytelling
    0.38
     craftsmanship
    0.38
     disparity
    0.37
     connectivity
    0.37
     experimentation
    0.37
    itude
    0.36
    ness
    0.35
     للغاية
    0.35
    Activations Density 0.117%

    No Known Activations