© 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. 64296
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
     también
    -1.06
     Turns
    -1.05
    yeah
    -1.02
     также
    -1.00
     publicités
    -0.99
    podob
    -0.98
     På
    -0.96
     Président
    -0.96
    Turns
    -0.95
    lossene
    -0.95
    POSITIVE LOGITS
     do
    1.57
     why
    1.52
     come
    1.27
     tell
    1.26
     what
    1.25
     pray
    1.23
     how
    1.21
     Why
    1.20
     have
    1.17
     by
    1.13
    Activations Density 0.013%

    No Known Activations