© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38784
    Prev
    Next
    INDEX
    Explanations

    words starting phrases

    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
    ()")
    -1.19
     your
    -1.15
     Kiedy
    -1.12
    $",
    -1.09
     baratas
    -1.05
     Jeśli
    -1.04
    ادث
    -1.02
     bordada
    -0.99
    игры
    -0.98
     cambiar
    -0.98
    POSITIVE LOGITS
    は
    1.13
    もあり
    1.12
    もあって
    1.09
    そこで
    1.04
    ┍
    1.03
     connections
    1.03
     presently
    1.02
    もありました
    1.02
    なども
    1.01
    についても
    1.01
    Activations Density 0.000%

    No Known Activations