© 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. 42002
    Prev
    Next
    INDEX
    Explanations

    absence of physiological traits

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    僰
    -3.27
    🫱
    -3.19
    邶
    -2.83
    蠓
    -2.81
    蹀
    -2.70
    呖
    -2.67
    いかない
    -2.56
    蓠
    -2.55
    ⟣
    -2.53
    殍
    -2.50
    POSITIVE LOGITS
    "
    3.27
    [
    3.05
    When
    2.97
    2
    2.88
    1
    2.77
     That
    2.73
    Once
    2.70
    With
    2.59
    與
    2.58
    There
    2.50
    Activations Density 0.001%

    No Known Activations