© 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. 10-GEMMASCOPE-RES-131K
    7. 20647
    Prev
    Next
    INDEX
    Explanations

    commands and instructions

    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_10/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
    their
    -1.88
    Should
    -1.41
     multe
    -1.38
    ulha
    -1.38
     constater
    -1.37
     itself
    -1.34
    蹓
    -1.30
    However
    -1.29
     enthou
    -1.29
     dowol
    -1.27
    POSITIVE LOGITS
    </b>
    1.63
    </h2>
    1.55
    </i>
    1.45
     هناك
    1.43
     не
    1.40
     There
    1.36
    </strong>
    1.34
    </em>
    1.32
     only
    1.32
     there
    1.30
    Activations Density 0.020%

    No Known Activations