© 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. 2329
    Prev
    Next
    INDEX
    Explanations

    grouping and subdivision

    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
    źnie
    0.61
    ън
    0.59
    עת
    0.59
    柺
    0.59
    য়ো
    0.59
    诮
    0.59
    Meri
    0.58
    یش
    0.57
     तरल
    0.57
    폄
    0.57
    POSITIVE LOGITS
     boundaries
    0.84
     grouping
    0.81
     folder
    0.80
     overarching
    0.80
     containing
    0.79
     groupings
    0.77
     subdivision
    0.76
     Boundaries
    0.76
     umbrella
    0.75
     समूह
    0.75
    Activations Density 0.010%

    No Known Activations