© 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. 131037
    Prev
    Next
    INDEX
    Explanations

    changed to or into

    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
     añadido
    -1.51
     ajutor
    -1.51
     manicura
    -1.48
     segítség
    -1.46
     tenuta
    -1.45
     móds
    -1.40
     támogat
    -1.40
     kérd
    -1.39
     nimic
    -1.39
     mög
    -1.38
    POSITIVE LOGITS
     to
    6.25
     into
    3.20
     onto
    1.52
     إلى
    1.46
     from
    1.38
    到
    1.37
    to
    1.34
     for
    1.26
    rrrrrrrr
    1.19
    至
    1.18
    Activations Density 0.075%

    No Known Activations