© 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. 78550
    Prev
    Next
    INDEX
    Explanations

    setters and code syntax

    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
    deinit
    -0.87
     Pollut
    -0.86
     devido
    -0.86
    了解更多
    -0.85
    umbnail
    -0.85
    necessarily
    -0.85
    around
    -0.84
     refuer
    -0.84
    格好
    -0.83
    ringes
    -0.83
    POSITIVE LOGITS
     will
    1.50
     void
    1.45
    void
    1.34
     set
    1.19
     would
    1.03
    将会
    0.88
    rodow
    0.88
    ITALY
    0.83
    セット
    0.83
     setzen
    0.82
    Activations Density 0.001%

    No Known Activations