© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75907
    Prev
    Next
    INDEX
    Explanations

    be understood, interpreted, construed

    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_34/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
    bilir
    -0.84
     során
    -0.80
    izh
    -0.77
    Speakers
    -0.77
     naming
    -0.76
     boca
    -0.76
    呼ば
    -0.76
    ய்
    -0.73
    cloned
    -0.72
     membuat
    -0.71
    POSITIVE LOGITS
     interpreted
    4.53
     interpret
    3.75
     interpretation
    3.73
    interpreted
    3.30
     interprets
    3.27
     interpreting
    3.23
     Interpretation
    3.20
    interpret
    3.17
     Interpre
    3.11
     Interpret
    3.08
    Activations Density 0.067%

    No Known Activations