© 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-16K
    7. 2604
    Prev
    Next
    INDEX
    Explanations

    counting zeroes

    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_16k_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
    िल
    2.95
    prav
    2.53
    쯤
    2.48
     बतौर
    2.35
    ह
    2.31
    ׁ
    2.31
    ности
    2.27
    vania
    2.27
    𝗘
    2.25
    Dios
    2.24
    POSITIVE LOGITS
    ش
    2.93
    ণ
    2.88
     önce
    2.35
    downcase
    2.34
    ბ
    2.32
    ć
    2.28
    ו
    2.27
    xff
    2.27
    +}^{
    2.24
     apert
    2.23
    Activations Density 0.124%

    No Known Activations