© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44710
    Prev
    Next
    INDEX
    Explanations

    we're going

    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
     Don
    -1.35
     Monaten
    -1.33
     seem
    -1.30
     That
    -1.27
    ”.
    -1.26
     penurunan
    -1.26
     után
    -1.26
    棗
    -1.26
     einzige
    -1.26
     ersten
    -1.25
    POSITIVE LOGITS
    ⅖
    1.45
     произошло
    1.43
     byen
    1.40
    ViewChild
    1.38
    coring
    1.34
    tych
    1.34
    ㈯
    1.34
    dicionado
    1.34
     ɛ
    1.34
    　　《
    1.33
    Activations Density 0.018%

    No Known Activations