© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 461
    Prev
    Next
    INDEX
    Explanations

    a body

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     głównie
    0.73
     tantôt
    0.69
     rarement
    0.68
     velmi
    0.67
     слегка
    0.66
    有些
    0.66
     légèrement
    0.66
    颇
    0.66
     relativement
    0.65
     altamente
    0.65
    POSITIVE LOGITS
     doubt
    1.34
     clue
    1.24
     discernible
    1.21
     hesitation
    1.16
     chance
    1.13
     shortage
    1.05
     regrets
    1.04
     rhyme
    1.03
     fanfare
    1.03
     excuses
    1.02
    Activations Density 1.037%

    No Known Activations