© 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. 31404
    Prev
    Next
    INDEX
    Explanations

    sql if exists

    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
    ücks
    -0.75
     lahir
    -0.72
    Sunset
    -0.71
     Conley
    -0.71
    ɭ
    -0.68
    ⒌
    -0.68
    Ор
    -0.67
     Conform
    -0.67
     ū
    -0.66
    ֩
    -0.66
    POSITIVE LOGITS
     educativos
    0.70
    listi
    0.65
    いて
    0.65
    fol
    0.65
     reflection
    0.64
    ilog
    0.64
    tificates
    0.63
     reprend
    0.63
     reprendre
    0.63
    الدرا
    0.63
    Activations Density 0.064%

    No Known Activations