© 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. 44715
    Prev
    Next
    INDEX
    Explanations

    reports and surveys

    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
    punten
    -1.49
    ŚĆ
    -1.41
    Insee
    -1.41
    ໌
    -1.41
     ไม่
    -1.36
    lastung
    -1.36
    非常
    -1.35
    ไม่มี
    -1.34
    我们
    -1.31
    laget
    -1.31
    POSITIVE LOGITS
     there
    1.45
     going
    1.42
    着一
    1.38
     different
    1.34
     another
    1.33
     any
    1.30
     now
    1.26
     their
    1.24
     in
    1.23
     even
    1.23
    Activations Density 0.059%

    No Known Activations