© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 6792
    Prev
    Next
    INDEX
    Explanations

    hole, opening, gap

    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_12_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
    ка
    1.60
    ри
    1.42
    it
    1.24
    i
    1.09
    is
    1.06
    are
    1.02
    ه
    0.99
    ে
    0.98
    ิ
    0.98
    id
    0.96
    POSITIVE LOGITS
     holes
    1.20
     отверсти
    1.18
     Holes
    1.07
     hole
    1.05
     craters
    1.02
     yawn
    1.01
     Hole
    0.99
     crevices
    0.97
     Mitra
    0.96
    няў
    0.96
    Activations Density 0.230%

    No Known Activations