© 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. 34-GEMMASCOPE-RES-131K
    7. 31125
    Prev
    Next
    INDEX
    Explanations

    starts direct speech

    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_34/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
     折りたたみ
    -1.13
    啃
    -1.08
    https
    -1.05
    dirent
    -1.04
    aka
    -1.02
    ian
    -1.02
     réinitial
    -1.02
     Antrieb
    -1.01
    >(</
    -0.98
     étroite
    -0.98
    POSITIVE LOGITS
     "
    2.80
     “
    2.63
     ”
    1.34
     „
    1.33
     «
    1.16
     berbeda
    1.07
     without
    1.05
     "";
    1.03
     "<<
    1.03
    setVerticalGroup
    1.00
    Activations Density 0.014%

    No Known Activations