© 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. 75158
    Prev
    Next
    INDEX
    Explanations

    actions and movements

    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
     on
    -1.51
     to
    -1.50
     beragam
    -1.40
     berusia
    -1.35
     is
    -1.35
     esos
    -1.29
    ейчас
    -1.24
    logías
    -1.24
    揖
    -1.23
     sebagainya
    -1.22
    POSITIVE LOGITS
     utilizza
    1.36
     befand
    1.31
    urangan
    1.30
    ३
    1.25
     στιγ
    1.25
     колеба
    1.17
     anything
    1.16
     disponível
    1.16
     ceea
    1.15
    繼續
    1.13
    Activations Density 0.024%

    No Known Activations