© 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. 128893
    Prev
    Next
    INDEX
    Explanations

    academic citations

    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
     piccoli
    -1.42
    ྄
    -1.34
     acht
    -1.31
     cuatro
    -1.28
     exklu
    -1.27
     oito
    -1.27
    ₃
    -1.27
     cinco
    -1.25
    hatenablog
    -1.25
    瘜
    -1.24
    POSITIVE LOGITS
     Regardless
    1.38
     принад
    1.31
    Regardless
    1.30
     unrelenting
    1.25
    With
    1.25
     Usually
    1.24
    While
    1.21
     Although
    1.20
     familières
    1.17
    起来的
    1.16
    Activations Density 0.017%

    No Known Activations