© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 692
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    ت
    1.33
     aider
    1.30
     Macquarie
    1.27
    ی
    1.27
     primaria
    1.25
     occult
    1.25
     educativos
    1.24
     Fundação
    1.24
     uzys
    1.24
    綦
    1.24
    POSITIVE LOGITS
    h
    0.86
    𝐡
    0.86
    flops
    0.85
    checker
    0.83
    al
    0.83
    ap
    0.82
    𝐞
    0.79
    ang
    0.78
     melt
    0.77
    ச்சி
    0.77
    Activations Density 0.072%

    No Known Activations