© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41598
    Prev
    Next
    INDEX
    Explanations

    places and conceptual continuums

    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
    蘩
    -2.52
    vantaged
    -2.34
    谞
    -2.30
    媗
    -2.20
     greateſt
    -2.19
    
    -2.14
    𝓶
    -2.09
    AutoresizingMask
    -2.09
    人の
    -2.06
     Testamento
    -2.06
    POSITIVE LOGITS
    s
    3.78
    the
    2.80
    u
    2.67
    h
    2.58
    ing
    2.45
    ers
    2.39
    &
    2.34
    m
    2.28
    .
    2.27
     '
    2.16
    Activations Density 0.008%

    No Known Activations