© 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. 57611
    Prev
    Next
    INDEX
    Explanations

    hashtags and @mentions

    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
    ▦
    -1.66
    toires
    -1.46
    Também
    -1.41
    蒟
    -1.41
    ЕРИ
    -1.41
    Aggi
    -1.39
     iNdEx
    -1.32
     dispu
    -1.30
     and
    -1.29
    ující
    -1.28
    POSITIVE LOGITS
    ↵↵
    1.47
     -
    1.36
     blanda
    1.35
     wachsen
    1.31
     rígida
    1.30
     abstracta
    1.29
    a
    1.28
     benutzen
    1.26
    栳
    1.23
    榀
    1.23
    Activations Density 0.018%

    No Known Activations