© 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. 19568
    Prev
    Next
    INDEX
    Explanations

    hereditary, homelessness, salivary gland conditions

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

    words related to medical and hereditary conditions such as "homelessness," "salivary," "hereditary," and "transcendental."

    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
    -3.72
    While
    -3.61
    After
    -3.36
    When
    -3.36
    One
    -3.34
    </h3>
    -3.31
    Many
    -3.22
    Only
    -3.20
    For
    -3.19
    Just
    -3.14
    POSITIVE LOGITS
    榦
    2.81
    隄
    2.77
    簠
    2.75
    缡
    2.70
    霂
    2.70
    舫
    2.63
     петербург
    2.59
    Erreferent
    2.58
    刄
    2.58
    鑁
    2.56
    Activations Density 0.023%

    No Known Activations