© 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. 22-GEMMASCOPE-RES-131K
    7. 9594
    Prev
    Next
    INDEX
    Explanations

    self, alcohol, relationships, sexual, resemblance

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

    academic terminology and psychological concepts in research papers.

    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_22/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
     siè
    -1.41
     cahier
    -1.40
     insanely
    -1.36
    キーボード
    -1.35
     sandero
    -1.35
    摇了
    -1.34
     vernis
    -1.34
    叼
    -1.32
    uric
    -1.31
     constater
    -1.31
    POSITIVE LOGITS
     information
    1.86
     their
    1.75
     or
    1.62
     epitom
    1.45
     one
    1.43
     items
    1.41
     presumably
    1.41
     focusing
    1.39
     during
    1.38
     primarily
    1.34
    Activations Density 0.203%

    No Known Activations