© 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. 10-GEMMASCOPE-RES-131K
    7. 73376
    Prev
    Next
    INDEX
    Explanations

    script prefixes

    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_10/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
     wartawan
    -1.57
    various
    -1.55
    欵
    -1.47
    something
    -1.43
    prevent
    -1.42
     something
    -1.39
     ſever
    -1.37
     différentes
    -1.36
    嫑
    -1.35
    extrémité
    -1.34
    POSITIVE LOGITS
     this
    1.92
     such
    1.77
     can
    1.63
     tillgäng
    1.42
     могат
    1.42
     olmak
    1.38
     would
    1.38
     ilyen
    1.35
    يمكن
    1.34
    This
    1.32
    Activations Density 0.004%

    No Known Activations