© 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. 33509
    Prev
    Next
    INDEX
    Explanations

    asking questions or making request

    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
     摆
    -1.02
     we
    -1.02
     Conferencia
    -0.96
     voyageurs
    -0.95
     multa
    -0.94
    🔗
    -0.92
     pipa
    -0.92
    ছে
    -0.91
    ffichage
    -0.91
     BIOLOGY
    -0.90
    POSITIVE LOGITS
     request
    2.05
     requesting
    2.02
     ask
    1.98
     asking
    1.96
     Request
    1.70
    request
    1.69
     Asking
    1.59
     requests
    1.55
     asked
    1.47
     Ask
    1.45
    Activations Density 0.047%

    No Known Activations