© 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. 34-GEMMASCOPE-RES-131K
    7. 77567
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and devices

    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
    蜂蜜
    -0.78
    Duel
    -0.77
     moindre
    -0.75
     publicKey
    -0.75
    culadora
    -0.75
    bullets
    -0.74
    Intrinsic
    -0.73
     crossed
    -0.73
    Purchasing
    -0.71
     marrying
    -0.70
    POSITIVE LOGITS
    illary
    1.52
    iliary
    1.20
    aux
    1.17
     Auxiliary
    1.13
     auxiliary
    1.11
    illi
    1.10
     Aux
    1.07
    Auxiliary
    1.06
    AUX
    1.05
     AUX
    1.05
    Activations Density 0.022%

    No Known Activations