© 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. 10844
    Prev
    Next
    INDEX
    Explanations

    assembled, 𝙍, 𝗹, assembled

    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
    ে
    5.21
    e
    5.15
    ej
    4.78
    ت
    4.75
    ei
    4.55
    ea
    4.48
    eh
    4.36
    اً
    4.32
    eau
    4.31
    ו
    4.30
    POSITIVE LOGITS
    sembled
    2.94
    𝙍
    2.83
    𝙇
    2.74
    に
    2.74
    𝙈
    2.71
    й
    2.66
    sembling
    2.57
    ynchronously
    2.50
    𝙎
    2.47
    ہ
    2.46
    Activations Density 0.154%

    No Known Activations