© 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. 10-GEMMASCOPE-RES-131K
    7. 14738
    Prev
    Next
    INDEX
    Explanations

    explanation of code or services

    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_10/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
    netje
    -1.49
     istället
    -1.40
     remboursement
    -1.32
    Gabriela
    -1.20
     hôtes
    -1.20
    jsko
    -1.19
    蕺
    -1.19
    зывы
    -1.19
    тов
    -1.18
    aría
    -1.17
    POSITIVE LOGITS
     aquellos
    1.43
     of
    1.41
    It
    1.38
    的人生
    1.36
     когда
    1.35
     who
    1.35
    :
    1.34
     well
    1.33
     when
    1.31
     though
    1.31
    Activations Density 0.246%

    No Known Activations