© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 1261
    Prev
    Next
    INDEX
    Explanations

    documents and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fenomeni
    0.79
    طلق
    0.78
    गमेंट
    0.75
    randn
    0.73
     fenómeno
    0.72
    ReLU
    0.70
     phénomènes
    0.70
    맛
    0.69
     возможностей
    0.69
    funktion
    0.69
    POSITIVE LOGITS
     documents
    2.19
     documentation
    2.01
     paperwork
    1.90
     spreadsheets
    1.81
     brochures
    1.80
     document
    1.75
     spreadsheet
    1.75
     transcripts
    1.72
     documentos
    1.69
     Documents
    1.67
    Activations Density 1.319%

    No Known Activations