© 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. 124707
    Prev
    Next
    INDEX
    Explanations

    I wanted to share

    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
     our
    -2.09
     respective
    -2.03
    汌
    -1.95
    ﱠ
    -1.85
     fährt
    -1.82
     determinados
    -1.80
     berühm
    -1.72
     defunct
    -1.68
     нынеш
    -1.68
    锒
    -1.66
    POSITIVE LOGITS
    1
    2.11
    3
    1.99
    7
    1.75
     tetapi
    1.74
    5
    1.63
     able
    1.62
    8
    1.60
    ’
    1.58
    让
    1.56
    2
    1.54
    Activations Density 0.030%

    No Known Activations