© 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. 9514
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
    ৢ
    -2.22
    Seven
    -2.17
    7
    -2.16
    Recently
    -2.03
    These
    -2.02
    說的
    -2.00
     Hinsicht
    -2.00
    6
    -2.00
     jahr
    -1.98
     вашего
    -1.97
    POSITIVE LOGITS
     We
    2.41
     not
    2.23
    es
    2.20
    喋
    1.86
     Our
    1.85
     Could
    1.80
     quiso
    1.78
     been
    1.77
    铩
    1.73
    ︓
    1.72
    Activations Density 0.025%

    No Known Activations