© 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. 129104
    Prev
    Next
    INDEX
    Explanations

    proximity to others or places

    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
    #
    -1.45
    になりますが
    -1.45
    individual
    -1.25
    歌唱
    -1.22
    '
    -1.22
    RUnlock
    -1.20
     You
    -1.20
    ayage
    -1.20
     "
    -1.19
    arket
    -1.19
    POSITIVE LOGITS
    Кита
    1.51
     where
    1.42
    ♪♪
    1.41
    ✳
    1.35
     justru
    1.31
     reportedly
    1.25
     Może
    1.25
     Terkait
    1.25
     Umfeld
    1.24
     Misalnya
    1.23
    Activations Density 0.028%

    No Known Activations