© 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. 102678
    Prev
    Next
    INDEX
    Explanations

    numbers and special characters

    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
    7
    -2.81
    5
    -2.64
     freaking
    -2.53
    6
    -2.52
    3
    -2.34
    4
    -2.33
     аккура
    -2.30
    ikuti
    -2.28
    8
    -2.25
    最初の
    -2.17
    POSITIVE LOGITS
    ↵
    2.66
    傒
    2.59
    ‘’
    2.56
    \
    2.44
    medriver
    2.44
     continúas
    2.44
     使い
    2.41
    梣
    2.38
    ?」
    2.25
    」,
    2.25
    Activations Density 0.187%

    No Known Activations