© 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. 34-GEMMASCOPE-RES-131K
    7. 63758
    Prev
    Next
    INDEX
    Explanations

    video file types and related technical terms

    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_34/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
     Dijo
    -0.81
     Incluso
    -0.81
     Algunas
    -0.78
     Diaspora
    -0.78
     Algunos
    -0.77
    teck
    -0.77
     vytvoř
    -0.76
    ㉗
    -0.75
    冪
    -0.73
    gods
    -0.72
    POSITIVE LOGITS
    forderungen
    0.94
     outlines
    0.86
    物的
    0.85
    எ
    0.82
     significado
    0.82
     álla
    0.81
     еды
    0.79
    AsStream
    0.79
    quez
    0.79
    hdr
    0.79
    Activations Density 0.027%

    No Known Activations