© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11652
    Prev
    Next
    INDEX
    Explanations

    AMA, ABA, AIS, Copa

    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
    乆
    -2.69
     ナビ
    -2.41
    穑
    -2.38
     AQUÍ
    -2.28
    iſe
    -2.22
     tiap
    -2.20
     theſe
    -2.16
     Ajoutez
    -2.16
     dage
    -2.16
     hij
    -2.16
    POSITIVE LOGITS
    the
    3.14
    but
    2.56
     and
    2.53
    ",
    2.36
    蠃
    2.31
    ၞ
    2.30
    an
    2.28
    as
    2.27
     obwohl
    2.25
    </strong>
    2.23
    Activations Density 0.008%

    No Known Activations