© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84285
    Prev
    Next
    INDEX
    Explanations

    as a minimum

    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
    eryllium
    -1.02
    ครับ
    -0.94
     Electromagnetic
    -0.92
     conseguiu
    -0.90
     snippetHide
    -0.90
     발생
    -0.87
     accelerometer
    -0.87
    λε
    -0.86
     organisé
    -0.86
     getElement
    -0.85
    POSITIVE LOGITS
     molar
    1.12
     facile
    1.12
     IUPAC
    1.09
    eqn
    1.00
     moles
    0.98
     plots
    0.97
     Guggenheim
    0.96
    experimental
    0.93
     emosi
    0.91
     деву
    0.91
    Activations Density 0.066%

    No Known Activations