© 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. 99443
    Prev
    Next
    INDEX
    Explanations

    journal abbreviations with periods

    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
    This
    -1.92
    The
    -1.81
    1
    -1.80
    Опис
    -1.75
     без
    -1.75
    9
    -1.73
     termasuk
    -1.72
    4
    -1.71
    5
    -1.70
     A
    -1.67
    POSITIVE LOGITS
     münchen
    2.22
     lác
    2.00
     heilig
    1.96
     récentes
    1.91
     filmen
    1.86
     étrang
    1.85
    ⡃
    1.84
     mineures
    1.83
    齮
    1.81
     rése
    1.80
    Activations Density 0.143%

    No Known Activations