© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 11940
    Prev
    Next
    INDEX
    Explanations

    gathering, collecting, accumulating

    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_16k_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
     Decre
    1.32
     μου
    1.28
     Venn
    1.27
     Fokker
    1.27
    년대
    1.25
    時
    1.25
    に
    1.23
    כם
    1.22
     WALK
    1.21
    ৯
    1.21
    POSITIVE LOGITS
    ة
    1.78
    gather
    1.59
    ing
    1.46
    funds
    1.42
     recueill
    1.38
    gathering
    1.32
    gathered
    1.24
    اندی
    1.24
    ру
    1.23
    accum
    1.23
    Activations Density 0.201%

    No Known Activations