© 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. 31743
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    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
     ヘッド
    -0.79
     でき
    -0.75
     Photo
    -0.73
    มือ
    -0.73
     commemor
    -0.73
    fenced
    -0.73
     stanov
    -0.72
     Ke
    -0.71
     Thumb
    -0.70
     Respuesta
    -0.69
    POSITIVE LOGITS
     endowed
    1.80
     equipped
    1.76
     endow
    1.52
     viewed
    1.48
     regarded
    1.48
    equipped
    1.38
     view
    1.27
     equipping
    1.17
     identification
    1.16
     equip
    1.15
    Activations Density 0.073%

    No Known Activations