© 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. 47448
    Prev
    Next
    INDEX
    Explanations

    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
    Sealed
    -0.86
     Sealed
    -0.85
     DECOR
    -0.79
    abha
    -0.78
     breakage
    -0.78
     Asthma
    -0.76
     Leung
    -0.76
     regulate
    -0.76
    vistar
    -0.76
     Arthritis
    -0.73
    POSITIVE LOGITS
     transfers
    1.63
     transfer
    1.36
     Transfers
    1.35
    Transfers
    1.34
    transfer
    1.30
    transfers
    1.26
    Transfer
    1.17
     Transfer
    1.16
    TRANSFER
    1.00
     transferencia
    0.98
    Activations Density 0.052%

    No Known Activations