© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54451
    Prev
    Next
    INDEX
    Explanations

    year author States Mecca offers

    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
    ⅽ
    -1.29
    картинка
    -1.22
    tranh
    -1.20
    тут
    -1.20
    набор
    -1.20
    诟
    -1.16
     ДЛЯ
    -1.14
     https
    -1.13
    なんだけど
    -1.13
     covid
    -1.11
    POSITIVE LOGITS
    かかり
    1.30
     BehaviorSubject
    1.22
     مخطط
    1.19
    īgas
    1.13
    .”
    1.13
    tinyurl
    1.12
     الحكومة
    1.11
    いただきたい
    1.09
    !”
    1.08
    ineros
    1.07
    Activations Density 0.034%

    No Known Activations