© 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. 10-GEMMASCOPE-RES-131K
    7. 123893
    Prev
    Next
    INDEX
    Explanations

    away from or from

    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
    狨
    -1.36
     crescere
    -1.33
    ᚕ
    -1.30
     αυτή
    -1.30
     popolazione
    -1.29
    ffè
    -1.28
     esclusivamente
    -1.28
    嵛
    -1.27
     transparence
    -1.27
     红色
    -1.27
    POSITIVE LOGITS
     from
    1.74
    m
    1.71
     \&
    1.64
    f
    1.61
    ;
    1.52
    ’
    1.45
     which
    1.39
    b
    1.38
    /
    1.38
    2
    1.37
    Activations Density 0.022%

    No Known Activations