© 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. 33198
    Prev
    Next
    INDEX
    Explanations

    method of programming

    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
     広場
    -1.37
    Pä
    -1.31
    Karakter
    -1.31
     fré
    -1.26
    卨
    -1.22
     perú
    -1.18
    Koordin
    -1.15
    媖
    -1.14
     菇
    -1.13
     ヌード
    -1.13
    POSITIVE LOGITS
    R
    1.29
     This
    1.29
     That
    1.24
    ^{\
    1.20
    It
    1.19
    T
    1.18
     Эта
    1.16
     --
    1.15
     These
    1.14
    G
    1.14
    Activations Density 0.172%

    No Known Activations