© 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. 2862
    Prev
    Next
    INDEX
    Explanations

    explaining concepts and analogies

    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
    אן
    0.49
     diantaranya
    0.45
     dernières
    0.43
     incluye
    0.42
     ，
    0.42
     suelen
    0.42
    चलित
    0.41
    各種
    0.41
    ﷼
    0.41
    )}\
    0.40
    POSITIVE LOGITS
     принци
    0.47
     phrasing
    0.47
    specificity
    0.46
     fundamentally
    0.46
     equivalence
    0.46
     valuing
    0.45
     verstehen
    0.44
     абстра
    0.44
     analogy
    0.44
     twofold
    0.43
    Activations Density 0.042%

    No Known Activations