© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4550
    Prev
    Next
    INDEX
    Explanations

    end of parenthetical examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_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
     thought
    0.74
     san
    0.73
     accordingly
    0.69
    ↵↵↵
    0.67
     sowie
    0.66
    并在
    0.66
     samt
    0.65
     erinnert
    0.65
    并将
    0.64
     અથવા
    0.64
    POSITIVE LOGITS
     wasps
    0.77
     GEAR
    0.76
    ರೆ
    0.75
     Bagley
    0.75
     Proud
    0.74
    nest
    0.74
    啤
    0.74
     CHE
    0.73
     Dough
    0.72
    ateurs
    0.72
    Activations Density 0.009%

    No Known Activations