© 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. 117127
    Prev
    Next
    INDEX
    Explanations

    license terms

    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
    耷
    -0.77
     blanda
    -0.75
    utrients
    -0.75
     conster
    -0.75
     bâton
    -0.72
    welijk
    -0.71
    communicate
    -0.71
     traduce
    -0.71
    conjugated
    -0.70
     ofere
    -0.69
    POSITIVE LOGITS
     driver
    0.78
     Slovakia
    0.74
     PVA
    0.74
     проб
    0.74
     advisory
    0.73
     out
    0.73
     appunto
    0.73
     adverb
    0.72
     tries
    0.72
    밖
    0.72
    Activations Density 0.013%

    No Known Activations