© 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. 104267
    Prev
    Next
    INDEX
    Explanations

    like, love, prefer, popularity

    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
    シップ
    -1.65
    !”
    -1.60
    If
    -1.55
    但他
    -1.55
    ﾋ
    -1.53
    The
    -1.51
    (^^)
    -1.41
    ❕
    -1.41
    ."
    -1.40
     time
    -1.35
    POSITIVE LOGITS
     -.
    1.45
     какой
    1.45
    はいけない
    1.37
     какую
    1.36
    </h1>
    1.36
    <i>
    1.35
    /.
    1.32
    aujourd
    1.31
    heng
    1.30
    堑
    1.30
    Activations Density 0.003%

    No Known Activations