© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31626
    Prev
    Next
    INDEX
    Explanations

    statistical analysis and specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مجازی
    -0.71
     sia
    -0.70
     kommt
    -0.69
    hant
    -0.68
     déf
    -0.67
    flutter
    -0.67
    zków
    -0.66
    嫖
    -0.66
     normas
    -0.66
    vimeo
    -0.65
    POSITIVE LOGITS
     pairwise
    1.67
     Tu
    1.61
    Tu
    1.43
     LSD
    1.35
    Multiple
    1.27
     Pair
    1.27
     post
    1.26
     contrasts
    1.24
    LSD
    1.22
     Dunn
    1.17
    Activations Density 0.016%

    No Known Activations