© 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. 65648
    Prev
    Next
    INDEX
    Explanations

    questions and code snippets

    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
    гою
    -1.03
    Possibly
    -1.00
     flota
    -0.99
    sprüng
    -0.99
    ANCHE
    -0.95
    大家好
    -0.94
    gingen
    -0.93
    ERICA
    -0.93
     balon
    -0.93
     grafic
    -0.93
    POSITIVE LOGITS
    נוּ
    0.98
     rotación
    0.93
    ̓
    0.92
     takich
    0.90
    Mediabestanden
    0.90
    了出去
    0.88
    Alike
    0.88
    נְ
    0.88
     femeninos
    0.86
    Kirchen
    0.85
    Activations Density 0.001%

    No Known Activations