© 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. 57525
    Prev
    Next
    INDEX
    Explanations

    amount and its transfer

    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
    kém
    -1.09
    zku
    -1.02
     esmalte
    -0.93
     and
    -0.93
    льные
    -0.91
     cabello
    -0.88
     revés
    -0.88
    tiéndose
    -0.88
    accompanied
    -0.87
    ┚
    -0.87
    POSITIVE LOGITS
     that
    1.98
     delivered
    1.88
     transferred
    1.77
     released
    1.66
     returned
    1.60
     entering
    1.55
     shipped
    1.53
     produced
    1.48
     sent
    1.48
     consumed
    1.48
    Activations Density 0.104%

    No Known Activations