© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103075
    Prev
    Next
    INDEX
    Explanations

    plants and facial features

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

    facial features or parts, particularly eyebrows, eyes, and other facial structures.

    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
     such
    -1.48
     ständig
    -1.44
     Ansprechpartner
    -1.41
    が欲しい
    -1.39
     нашел
    -1.34
    素晴らしい
    -1.31
    <h2>
    -1.30
     particular
    -1.29
    他也
    -1.28
    ate
    -1.27
    POSITIVE LOGITS
    lblNewLabel
    1.49
    readFileSync
    1.34
    initializeApp
    1.31
    дания
    1.31
     wegen
    1.30
    centerTitle
    1.30
    蒾
    1.26
    芣
    1.25
    AfterViewInit
    1.25
    estä
    1.24
    Activations Density 0.022%

    No Known Activations