© 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. 44315
    Prev
    Next
    INDEX
    Explanations

    company

    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
     \%$
    -1.82
    皛
    -1.79
    inture
    -1.70
    </sup>
    -1.60
    atschapp
    -1.56
     搞笑
    -1.55
    ChildScrollView
    -1.50
    mée
    -1.47
     巾
    -1.47
    neten
    -1.46
    POSITIVE LOGITS
    :
    2.31
     an
    1.98
     just
    1.66
     a
    1.49
    er
    1.48
     one
    1.48
    ar
    1.46
     relevant
    1.41
     explicou
    1.41
    /
    1.39
    Activations Density 0.023%

    No Known Activations