© 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. 116110
    Prev
    Next
    INDEX
    Explanations

    Lawyers, numbers, symbols, code

    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
     took
    -1.70
     before
    -1.68
     will
    -1.67
     when
    -1.63
     by
    -1.58
     if
    -1.53
     during
    -1.53
     with
    -1.52
     at
    -1.50
     any
    -1.48
    POSITIVE LOGITS
     trám
    1.52
    
    1.46
     cúp
    1.43
    Recept
    1.42
     null
    1.38
     Dinas
    1.35
     Atención
    1.34
     faciliter
    1.32
    Presenta
    1.32
     NaN
    1.31
    Activations Density 0.003%

    No Known Activations