© 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. 7102
    Prev
    Next
    INDEX
    Explanations

    code, config, and programming languages

    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
     unparalleled
    -1.01
     exquisitely
    -1.01
     plethora
    -1.01
    hydrogenase
    -0.98
     meticulously
    -0.98
    <0xD2>
    -0.97
     симпто
    -0.92
     expertly
    -0.92
    Codice
    -0.90
     flimsy
    -0.90
    POSITIVE LOGITS
     এবং
    1.01
     CHE
    1.00
     comenzará
    0.99
    andering
    0.99
     மற்றும்
    0.96
    actually
    0.96
     llegará
    0.96
     so
    0.95
     spectacular
    0.94
     VERY
    0.94
    Activations Density 0.062%

    No Known Activations