© 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. 14
    Prev
    Next
    INDEX
    Explanations

    file names and keywords

    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
     Lyapunov
    0.75
     OPEC
    0.71
     JFK
    0.71
    <unused385>
    0.71
     solvable
    0.71
     monoclonal
    0.70
     USGS
    0.69
     tumultuous
    0.69
     PCR
    0.69
     JPL
    0.68
    POSITIVE LOGITS
    画面
    0.53
    ר
    0.52
    팍
    0.50
    ্স
    0.50
    もので
    0.50
    פה
    0.46
     ورو
    0.45
    ť
    0.45
    Lol
    0.44
    Hi
    0.43
    Activations Density 0.938%

    No Known Activations