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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 288
    Prev
    Next
    INDEX
    Explanations

    here's a breakdown

    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_22_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
     дру
    0.78
     முடியாது
    0.73
    жидан
    0.70
    蹟
    0.70
     여기까지
    0.69
     മറ
    0.67
     voort
    0.67
     Ceremony
    0.67
     Rights
    0.66
    ModuleName
    0.65
    POSITIVE LOGITS
    '
    0.91
     are
    0.89
    ’
    0.84
    %'
    0.68
    Are
    0.67
     is
    0.66
     comes
    0.63
     sont
    0.63
     grap
    0.63
    inafter
    0.62
    Activations Density 0.496%

    No Known Activations