© 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. 66789
    Prev
    Next
    INDEX
    Explanations

    non-english characters or common english words

    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
    viembre
    -2.75
    蛩
    -2.69
    殂
    -2.67
    </h3>
    -2.64
    坼
    -2.63
    ઁ
    -2.58
     thier
    -2.53
     zahlreiche
    -2.44
    塤
    -2.42
    骓
    -2.41
    POSITIVE LOGITS
    1
    3.67
    '
    3.19
     The
    3.13
    9
    2.98
    8
    2.88
    4
    2.81
    a
    2.75
    2
    2.69
    7
    2.66
     We
    2.63
    Activations Density 0.001%

    No Known Activations