© 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. 57589
    Prev
    Next
    INDEX
    Explanations

    to + destination or state

    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
    𓆏
    -2.55
     fidé
    -2.47
     Dinas
    -2.42
     ส์
    -2.28
     différents
    -2.25
     guapos
    -2.23
    𓁹
    -2.23
     dévelo
    -2.22
    ఽ
    -2.22
     célè
    -2.20
    POSITIVE LOGITS
     to
    3.13
     in
    2.86
     from
    2.70
     with
    2.70
     as
    2.69
     on
    2.67
     for
    2.61
     only
    2.58
     will
    2.42
     just
    2.31
    Activations Density 0.042%

    No Known Activations