© 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. 22-GEMMASCOPE-RES-131K
    7. 16184
    Prev
    Next
    INDEX
    Explanations

    film release details

    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_22/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
     for
    -1.13
    וּ
    -1.06
     tesis
    -1.03
    openConnection
    -1.00
     diagrama
    -0.96
    Koordinaten
    -0.95
     RECOMMEND
    -0.94
    größern
    -0.94
     више
    -0.92
    )।
    -0.91
    POSITIVE LOGITS
     later
    1.20
    ⅝
    1.04
    htaccess
    1.04
    "}";
    1.02
    ările
    0.98
    tôi
    0.94
    camis
    0.93
    cách
    0.93
     recently
    0.92
    ampilkan
    0.92
    Activations Density 0.002%

    No Known Activations