© 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. 10-GEMMASCOPE-RES-131K
    7. 20254
    Prev
    Next
    INDEX
    Explanations

    variable i in loops

    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
     in
    -2.75
     on
    -2.52
     to
    -2.45
     which
    -2.44
     for
    -2.44
     from
    -2.34
     at
    -2.33
     them
    -2.33
     of
    -2.27
     They
    -2.08
    POSITIVE LOGITS
    _
    2.56
    >
    2.45
    \
    2.41
     использовании
    2.36
    킁
    2.34
    _{
    2.33
    $
    2.33
    If
    2.31
    after
    2.30
    6
    2.28
    Activations Density 0.006%

    No Known Activations