© 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. 130486
    Prev
    Next
    INDEX
    Explanations

    numbers and identifiers

    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
    蛧
    -1.68
     abstrato
    -1.42
    גם
    -1.38
    鹀
    -1.37
     farb
    -1.37
     cães
    -1.37
     peixes
    -1.37
    铼
    -1.35
     alſo
    -1.34
     fullt
    -1.33
    POSITIVE LOGITS
     not
    1.70
     for
    1.63
     in
    1.49
     insisted
    1.30
     delivered
    1.30
    ならない
    1.29
    黩
    1.26
     they
    1.24
     with
    1.21
     a
    1.20
    Activations Density 0.013%

    No Known Activations