© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1831
    Prev
    Next
    INDEX
    Explanations

    introducing lists or examples

    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
    着一个
    -1.21
     two
    -1.07
    certain
    -1.04
    рія
    -1.02
    pearance
    -1.00
    ysteem
    -1.00
     plurality
    -0.97
    cive
    -0.96
     какой
    -0.93
     Steuerung
    -0.90
    POSITIVE LOGITS
     examples
    2.36
     notable
    1.94
     ways
    1.86
     example
    1.77
     reasons
    1.66
     of
    1.63
     possible
    1.56
     highlights
    1.48
     noteworthy
    1.48
    Examples
    1.41
    Activations Density 0.047%

    No Known Activations