© 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-262K
    7. 9682
    Prev
    Next
    INDEX
    Explanations

    medium risk, hold, or priority

    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
    ط
    2.84
    이
    2.80
    й
    2.72
    на
    2.61
    ை
    2.58
    ী
    2.56
    ment
    2.48
    نا
    2.47
    м
    2.43
     coinc
    2.43
    POSITIVE LOGITS
    𝐠
    3.27
    𝐢
    3.20
    𝐚
    3.00
    𝐨
    2.98
    𝐥
    2.97
    𝐝
    2.95
    𝐧
    2.94
    𝐞
    2.93
    eiros
    2.92
    𝐣
    2.85
    Activations Density 0.088%

    No Known Activations