© 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-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1860
    Prev
    Next
    INDEX
    Explanations

    typically have

    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_9_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
    est
    1.18
    йно
    0.98
     gerne
    0.97
    était
    0.96
     சேர்த்து
    0.89
     gern
    0.88
    ో
    0.87
    danger
    0.87
    predictors
    0.83
    Easing
    0.82
    POSITIVE LOGITS
    xiety
    1.05
     twenties
    1.02
    ched
    0.97
    驒
    0.96
    িং
    0.96
     fadeIn
    0.94
    
    0.93
     vitamins
    0.91
     falando
    0.91
    עות
    0.90
    Activations Density 0.578%

    No Known Activations