© 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. 87151
    Prev
    Next
    INDEX
    Explanations

    structured data or lists

    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
     it
    -1.44
     început
    -1.42
    ’，
    -1.41
     any
    -1.38
    逍
    -1.35
     venit
    -1.31
    
    -1.30
     our
    -1.27
    "]];
    -1.27
    Schule
    -1.26
    POSITIVE LOGITS
     разных
    1.68
    mostly
    1.57
    4
    1.53
    including
    1.47
    2
    1.45
    Always
    1.44
    with
    1.41
    well
    1.41
    You
    1.40
    Your
    1.38
    Activations Density 0.139%

    No Known Activations