© 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. 65140
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions enclosed in $$

    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
     because
    -2.45
    There
    -2.45
     namun
    -2.42
     should
    -2.41
     in
    -2.31
    there
    -2.31
     at
    -2.27
     or
    -2.22
    They
    -2.22
    With
    -2.20
    POSITIVE LOGITS
    笮
    3.20
    筇
    2.52
    ating
    2.52
    ྂ
    2.45
    骤
    2.39
     douze
    2.36
     letzte
    2.34
     habile
    2.33
     alté
    2.33
     velké
    2.30
    Activations Density 0.002%

    No Known Activations