© 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. 10-GEMMASCOPE-RES-131K
    7. 130739
    Prev
    Next
    INDEX
    Explanations

    "Working with", "Role of", "Comparison of", "Hard Rock", "Why there", "Free market", "Create var", "Experimental animal"

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

    titles or introductory phrases that describe a topic or subject matter.

    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
     of
    -1.99
     така
    -1.44
     清新
    -1.38
     —
    -1.27
    Ended
    -1.23
    鯵
    -1.22
    increased
    -1.22
     EACH
    -1.20
     then
    -1.19
    CONCLUS
    -1.19
    POSITIVE LOGITS
     when
    1.74
     to
    1.55
     cumbersome
    1.54
    when
    1.50
     When
    1.50
     troubling
    1.47
     enticing
    1.44
    When
    1.43
     because
    1.38
     However
    1.37
    Activations Density 0.311%

    No Known Activations