© 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. 103899
    Prev
    Next
    INDEX
    Explanations

    ties and relations

    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
    )]
    -1.58
     also
    -1.52
     Fotografía
    -1.50
     acuarela
    -1.45
     también
    -1.43
    ()])
    -1.41
    btnut
    -1.35
    老祖
    -1.34
    你也
    -1.34
    셉
    -1.32
    POSITIVE LOGITS
    d
    1.48
     poderia
    1.43
    it
    1.30
     -------
    1.29
     llego
    1.27
    2
    1.27
     quarre
    1.22
    づらい
    1.20
     Таким
    1.17
    まあ
    1.16
    Activations Density 0.015%

    No Known Activations