© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21153
    Prev
    Next
    INDEX
    Explanations

    statement or suggestion from someone

    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
     to
    -1.62
    ibatis
    -1.18
    ၟ
    -1.16
    Халы
    -1.15
    циональный
    -1.13
     dramatically
    -1.13
     of
    -1.13
    excerpt
    -1.12
     radically
    -1.11
    钲
    -1.11
    POSITIVE LOGITS
     then
    1.47
    seemed
    1.37
    
    1.30
    wants
    1.27
     they
    1.23
     premières
    1.20
     next
    1.18
    moved
    1.17
    ns
    1.16
    cers
    1.16
    Activations Density 0.077%

    No Known Activations