© 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. 15219
    Prev
    Next
    INDEX
    Explanations

    legal case and court documents

    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
    a
    -4.09
    t
    -3.42
    e
    -3.42
    u
    -3.36
    or
    -3.36
    o
    -3.34
    i
    -3.30
    ar
    -3.13
    j
    -2.78
    簓
    -2.73
    POSITIVE LOGITS
    The
    2.64
    вать
    2.56
     Partager
    2.47
    轳
    2.38
    は
    2.38
    ally
    2.36
    ↵
    2.31
    
    2.31
    detek
    2.30
     Belakang
    2.30
    Activations Density 0.003%

    No Known Activations