© 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. 9722
    Prev
    Next
    INDEX
    Explanations

    ratio of

    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
    我們
    -2.06
     или
    -1.98
     یا
    -1.92
    ússia
    -1.89
    ྥ
    -1.85
    jestel
    -1.84
    錵
    -1.82
    ?”
    -1.81
     and
    -1.81
    產品
    -1.78
    POSITIVE LOGITS
    '
    2.33
    ↵
    2.00
    e
    1.96
    "
    1.93
    ratio
    1.89
     between
    1.88
    son
    1.88
    きちんと
    1.87
    使った
    1.87
     ratios
    1.84
    Activations Density 0.040%

    No Known Activations