© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 33392
    Prev
    Next
    INDEX
    Explanations

    word versus word

    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_22/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
     prière
    -1.10
     ceux
    -0.97
    pork
    -0.97
    ssis
    -0.96
    verick
    -0.96
     abends
    -0.96
     pensée
    -0.96
     déclaration
    -0.95
    Bacon
    -0.92
    飨
    -0.91
    POSITIVE LOGITS
     this
    1.51
     our
    1.12
    this
    1.11
     him
    1.02
     män
    0.98
     vilja
    0.95
    ALLY
    0.93
     signifikan
    0.93
    Földrajz
    0.93
    him
    0.91
    Activations Density 0.067%

    No Known Activations