© 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. 119775
    Prev
    Next
    INDEX
    Explanations

    cards

    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
    ’
    -3.08
     '
    -2.75
    Ꭳ
    -2.53
    ll
    -2.33
    l
    -2.31
    ing
    -2.28
    ୌ
    -2.27
    er
    -2.19
    medriver
    -2.19
    3
    -2.17
    POSITIVE LOGITS
    Therefore
    2.42
    of
    2.25
    ihr
    2.19
     greateſt
    2.11
    lusst
    2.00
     cards
    1.99
    忍受
    1.95
    Thus
    1.95
    In
    1.92
    いを
    1.91
    Activations Density 0.005%

    No Known Activations