© 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. 10-GEMMASCOPE-RES-131K
    7. 112520
    Prev
    Next
    INDEX
    Explanations

    behavior of

    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
    řízen
    -1.66
    sukienka
    -1.63
     destrucción
    -1.63
    ſtion
    -1.59
    BIÉN
    -1.59
     appetizers
    -1.54
    Ř
    -1.52
    🔸
    -1.52
    こんに
    -1.49
    bluza
    -1.48
    POSITIVE LOGITS
     of
    2.47
    7
    2.06
    if
    1.84
    8
    1.81
    9
    1.75
    6
    1.74
    K
    1.72
     if
    1.70
    x
    1.66
    on
    1.65
    Activations Density 0.050%

    No Known Activations