© 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. 39503
    Prev
    Next
    INDEX
    Explanations

    web component tags

    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
     passieren
    -1.61
     unusually
    -1.52
    řízen
    -1.50
     oddly
    -1.49
     senaste
    -1.46
     preciosa
    -1.42
     may
    -1.41
     horribly
    -1.41
     besök
    -1.38
     unusual
    -1.38
    POSITIVE LOGITS
     this
    1.46
     et
    1.33
    all
    1.32
     nowe
    1.31
     \&
    1.30
    ㍉
    1.29
    whose
    1.29
     we
    1.28
    besides
    1.28
    we
    1.25
    Activations Density 0.015%

    No Known Activations