© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 10331
    Prev
    Next
    INDEX
    Explanations

    HSV, driving, neighbor,stoffe

    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
    ку
    1.66
    ϴ
    1.46
    𓍊
    1.38
     inwardly
    1.38
    ☑
    1.37
    <0x1C>
    1.35
    פו
    1.35
    ು
    1.34
    🟠
    1.33
    ➘
    1.33
    POSITIVE LOGITS
    𝘨
    1.24
     creative
    1.22
    आ
    1.18
    oltre
    1.17
     conquist
    1.15
     cread
    1.14
    𝘵
    1.12
    𝘥
    1.10
    調理
    1.10
     journe
    1.06
    Activations Density 0.000%

    No Known Activations