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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100705
    Prev
    Next
    INDEX
    Explanations

    small amounts or degrees

    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
    unfortunately
    -1.55
    pls
    -1.54
    basically
    -1.50
    dengan
    -1.47
    actually
    -1.41
    presumably
    -1.40
     veren
    -1.38
    essentially
    -1.38
    ครื่อง
    -1.38
     tambien
    -1.38
    POSITIVE LOGITS
     this
    2.70
     which
    1.75
     such
    1.74
     puts
    1.63
     starts
    1.60
    When
    1.55
     was
    1.55
     reduces
    1.50
     could
    1.49
     takes
    1.47
    Activations Density 0.017%

    No Known Activations