© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104104
    Prev
    Next
    INDEX
    Explanations

    predicting SUD

    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
     «
    -1.45
     but
    -1.38
     „
    -1.18
     :
    -1.17
     •
    -1.17
     hefyd
    -1.13
     """
    -1.13
    «
    -1.13
    _
    -1.11
     \
    -1.10
    POSITIVE LOGITS
     本店
    1.24
    五日
    1.22
    зации
    1.20
    őben
    1.20
     лента
    1.18
    Einstellungen
    1.18
     невели
    1.17
     Würde
    1.16
     Фото
    1.16
    객체
    1.16
    Activations Density 0.318%

    No Known Activations