© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12502
    Prev
    Next
    INDEX
    Explanations

    voicings and voice

    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
    Negative Logits
    𝐝
    3.52
    নি
    3.36
    𝐀
    3.34
    𝐫
    3.31
    𝐂
    3.25
    𝐧
    3.17
    EK
    3.15
    𝐍
    3.10
    ে
    2.95
    𝐣
    2.91
    POSITIVE LOGITS
    ️
    3.24
    ︎
    3.13
    ен
    2.76
    ीय
    2.63
    र्गत
    2.45
    ہ
    2.45
    ే
    2.34
    UAGES
    2.34
    onent
    2.33
    够
    2.32
    Activations Density 0.040%

    No Known Activations