© 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. 9245
    Prev
    Next
    INDEX
    Explanations

    highlighting important details

    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
     Euclid
    0.46
     angios
    0.46
    㖮
    0.45
     combinaison
    0.44
     digestibility
    0.44
     acabó
    0.44
     combinação
    0.44
    迌
    0.43
     catálogo
    0.42
    㣩
    0.42
    POSITIVE LOGITS
    important
    0.62
     parts
    0.53
    parts
    0.53
    重要的
    0.52
    optional
    0.50
    Important
    0.50
     important
    0.49
     গুরুত্বপূর্ণ
    0.48
     مهم
    0.48
     Important
    0.47
    Activations Density 0.113%

    No Known Activations