© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2988
    Prev
    Next
    INDEX
    Explanations

    counting or quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     subjug
    0.31
    𒉣
    0.27
     अनुरूप
    0.27
     vuln
    0.26
    뀔
    0.26
     doubtless
    0.26
     społ
    0.26
     zrozum
    0.26
    业界
    0.26
    权威
    0.26
    POSITIVE LOGITS
     five
    0.33
     three
    0.31
     each
    0.30
     twice
    0.30
     randomly
    0.29
     A
    0.29
     four
    0.28
     two
    0.28
     $
    0.28
     Calculate
    0.27
    Activations Density 0.134%

    No Known Activations