© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60822
    Prev
    Next
    INDEX
    Explanations

    names and individuals

    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
    \
    -2.88
     we
    -2.88
     руках
    -2.59
    *
    -2.48
    」
    -2.41
     голове
    -2.36
    )?
    -2.36
    â
    -2.28
     they
    -2.25
     atau
    -2.23
    POSITIVE LOGITS
    OUTUBE
    2.92
    嵎
    2.25
    örté
    2.25
     vó
    2.20
     historische
    2.17
     They
    2.13
    亟
    2.11
    痦
    2.09
     vorige
    2.09
     ظهر
    2.08
    Activations Density 0.007%

    No Known Activations