© 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. 10-GEMMASCOPE-RES-131K
    7. 7726
    Prev
    Next
    INDEX
    Explanations

    April Fool's, turtles, mutant, sewers

    np_acts-logits-general · gemini-2.5-flash-lite

    proper nouns including character names, brands, titles, and franchises.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     the
    -1.49
     et
    -1.48
     my
    -1.38
     programmi
    -1.30
     avon
    -1.30
     chiesa
    -1.28
    说
    -1.28
    so
    -1.28
    oinette
    -1.27
     чинов
    -1.26
    POSITIVE LOGITS
    ྃ
    1.70
     ciento
    1.45
    IBar
    1.42
     reconoció
    1.41
     sewers
    1.39
     integrados
    1.30
     lluvias
    1.30
     sumamente
    1.28
     editados
    1.28
     sewer
    1.28
    Activations Density 0.006%

    No Known Activations