© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10680
    Prev
    Next
    INDEX
    Explanations

    conditional code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     minhas
    1.02
     '}
    0.93
    ⌞
    0.91
     /*
    0.90
     capuche
    0.88
     serían
    0.87
     solidaridad
    0.86
     എന്റെ
    0.86
     impuestos
    0.86
     renderEncoder
    0.86
    POSITIVE LOGITS
    ens
    0.72
    estan
    0.64
    begin
    0.63
    ;;
    0.62
    end
    0.60
    let
    0.59
     hook
    0.59
    ension
    0.59
     hooked
    0.57
    have
    0.57
    Activations Density 0.070%

    No Known Activations