© 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. 73953
    Prev
    Next
    INDEX
    Explanations

    exclamations and interjections

    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
    StrictEqual
    -1.20
     vairāk
    -1.20
     a
    -1.16
    chauen
    -1.16
    feest
    -1.12
    connect
    -1.10
    ος
    -1.06
    JsonObject
    -1.06
     kompakt
    -1.04
    historie
    -1.03
    POSITIVE LOGITS
     周辺
    1.21
    婭
    1.20
     nawet
    1.17
    쨰
    1.17
     didn
    1.13
    あるので
    1.13
     how
    1.05
     ifølge
    1.04
    甚至是
    1.03
    ようです
    1.02
    Activations Density 0.146%

    No Known Activations