© 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. 66842
    Prev
    Next
    INDEX
    Explanations

    mathematical vectors or bar notations

    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
    ↵
    -3.08
    ’
    -2.33
     to
    -2.20
     cortada
    -1.98
    ᡵ
    -1.92
    眥
    -1.91
     as
    -1.91
     särskilt
    -1.89
     negra
    -1.87
    símbolo
    -1.86
    POSITIVE LOGITS
     the
    3.11
    簟
    2.61
    鶺
    2.55
    埽
    2.45
    to
    2.44
    윔
    2.41
    妡
    2.38
     niedersachsen
    2.36
     GOtt
    2.36
    泐
    2.31
    Activations Density 0.002%

    No Known Activations