© 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. 12295
    Prev
    Next
    INDEX
    Explanations

    Legal, medical, and technical terms

    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
    $+
    1.46
    े
    1.35
     डिप्टी
    1.33
     Carb
    1.28
     unto
    1.27
    CCP
    1.26
    isEqualTo
    1.24
    Ripple
    1.24
    TextChanged
    1.23
    व
    1.23
    POSITIVE LOGITS
    lardan
    1.34
     dotycz
    1.32
    ล์
    1.28
    امہ
    1.26
    आई
    1.24
    هُ
    1.22
    us
    1.21
    äts
    1.18
    ্টি
    1.17
    те
    1.16
    Activations Density 0.000%

    No Known Activations