© 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. 31185
    Prev
    Next
    INDEX
    Explanations

    not a substitute or admission

    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
     mostly
    -1.02
     almost
    -1.02
     mainly
    -0.96
     very
    -0.96
     basically
    -0.95
     well
    -0.91
     distinctly
    -0.90
     through
    -0.89
     utilizan
    -0.89
     albeit
    -0.87
    POSITIVE LOGITS
     substitute
    1.74
     exhaustive
    1.55
     endorsement
    1.41
     substitutes
    1.38
    substitute
    1.30
     guarantee
    1.27
     definitive
    1.24
    endor
    1.23
     replacement
    1.22
    replace
    1.20
    Activations Density 0.072%

    No Known Activations