© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128878
    Prev
    Next
    INDEX
    Explanations

    started dating

    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
     realizar
    -1.45
     heutigen
    -1.31
     três
    -1.31
    u
    -1.30
     gemeinsamen
    -1.28
     новых
    -1.27
     will
    -1.27
     ofrece
    -1.26
    but
    -1.25
     You
    -1.23
    POSITIVE LOGITS
    みなさん
    1.55
    ANTAGES
    1.52
    Morfo
    1.36
    🔰
    1.29
    また
    1.28
    Ď
    1.28
    viève
    1.27
    ⠐
    1.26
    лтемелер
    1.24
     Büyük
    1.24
    Activations Density 0.016%

    No Known Activations