© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 21770
    Prev
    Next
    INDEX
    Explanations

    By | Commentary

    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
     คา
    -1.43
    EXHIBIT
    -1.36
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.36
     всички
    -1.35
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.34
     cincuenta
    -1.32
     laiton
    -1.30
    艹
    -1.30
     chré
    -1.29
    ществует
    -1.29
    POSITIVE LOGITS
     have
    1.88
     by
    1.74
     with
    1.54
     didn
    1.46
     not
    1.46
     we
    1.46
     some
    1.44
     haven
    1.42
     now
    1.39
     regarding
    1.38
    Activations Density 0.032%

    No Known Activations