© 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. 65730
    Prev
    Next
    INDEX
    Explanations

    Copyright notices and licenses

    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
     to
    -0.93
    ất
    -0.82
     umgekehrt
    -0.80
    霜
    -0.80
     rzecz
    -0.79
     angewendet
    -0.79
     tussen
    -0.77
     its
    -0.77
    itively
    -0.77
    Its
    -0.77
    POSITIVE LOGITS
     mesmos
    1.02
    라고
    0.88
    чков
    0.88
     dortmund
    0.86
    ריה
    0.86
     logan
    0.86
    ורי
    0.86
     listes
    0.83
     frambo
    0.82
    بله
    0.82
    Activations Density 0.108%

    No Known Activations