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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 15
    Prev
    Next
    INDEX
    Explanations

    month names

    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
    
    1.25
     bargaining
    1.15
    
    1.10
    Ча
    1.09
     embarrassing
    1.08
    
    1.06
    柢
    1.05
    --',
    1.05
    妣
    1.05
    Dtos
    1.04
    POSITIVE LOGITS
    u
    1.36
    in
    1.10
    та
    1.08
    са
    0.97
    ро
    0.96
    un
    0.94
    uq
    0.93
    t
    0.91
    uš
    0.89
    ientes
    0.88
    Activations Density 0.080%

    No Known Activations