© 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-262K
    7. 12035
    Prev
    Next
    INDEX
    Explanations

    fuse box

    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_262k_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
    ू
    2.65
    𝐨
    2.39
    zeugung
    2.37
    ב
    2.31
    ার
    2.25
    ე
    2.19
    로
    2.17
    ist
    2.10
    澜
    2.07
    ise
    2.06
    POSITIVE LOGITS
    ੀ
    2.90
    ا
    2.85
    री
    2.79
     rites
    2.76
    Појединачна
    2.74
     laugh
    2.72
     shutout
    2.71
    𝑟
    2.71
    e
    2.70
     calm
    2.62
    Activations Density 0.003%

    No Known Activations