© 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. 10-GEMMASCOPE-RES-131K
    7. 15353
    Prev
    Next
    INDEX
    Explanations

    horses and riding

    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
    e
    -1.46
     удачи
    -1.28
     eaux
    -1.27
     соответ
    -1.22
     blancs
    -1.20
     herbes
    -1.19
     frapp
    -1.18
    considered
    -1.16
    s
    -1.15
    フード
    -1.13
    POSITIVE LOGITS
    ”?
    1.27
     numerosos
    1.25
     about
    1.21
    滬
    1.17
    ).
    1.16
    KEYCODE
    1.14
    гать
    1.13
    𝘌
    1.13
    ).”
    1.13
    PostInfinity
    1.13
    Activations Density 0.034%

    No Known Activations