© 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. 3150
    Prev
    Next
    INDEX
    Explanations

    contrast and comparisons

    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
     you
    -1.40
     what
    -1.31
     one
    -1.29
     ſi
    -1.09
     biasanya
    -1.09
     your
    -1.02
    iramente
    -1.02
    роятно
    -1.01
     minutter
    -1.01
    潜力
    -0.99
    POSITIVE LOGITS
     the
    1.63
     no
    1.55
     significant
    1.53
     highest
    1.52
     overall
    1.47
    significant
    1.46
    highest
    1.38
     lowest
    1.34
     only
    1.32
     higher
    1.32
    Activations Density 0.188%

    No Known Activations