© 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. 22-GEMMASCOPE-RES-131K
    7. 128626
    Prev
    Next
    INDEX
    Explanations

    names and locations

    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_22/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
    Enregistrer
    -1.38
    imgdir
    -1.37
     pengobatan
    -1.36
     technical
    -1.34
     tfsi
    -1.31
    に於
    -1.29
     narkoba
    -1.27
    Spécifications
    -1.27
    Conseils
    -1.24
    اقرأ
    -1.23
    POSITIVE LOGITS
    וּ
    1.52
    เรา
    1.40
     fieldwork
    1.25
     travaillé
    1.23
    政治
    1.19
    ﻻ
    1.19
     zvuky
    1.16
     cír
    1.16
    ־ה
    1.16
    公共
    1.15
    Activations Density 0.050%

    No Known Activations