© 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. 58209
    Prev
    Next
    INDEX
    Explanations

    that + action

    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
     for
    -1.30
     द्वारा
    -1.07
     трябва
    -0.99
     by
    -0.98
     menjal
    -0.97
     choose
    -0.96
     decide
    -0.95
     during
    -0.94
    unless
    -0.94
    if
    -0.90
    POSITIVE LOGITS
     meet
    1.29
     respects
    1.27
     will
    1.27
     meets
    1.27
    ۰۱
    1.25
     fit
    1.24
     fits
    1.21
     réellement
    1.16
     suits
    1.16
    reflect
    1.15
    Activations Density 0.070%

    No Known Activations