© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66889
    Prev
    Next
    INDEX
    Explanations

    specific nouns

    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
     itself
    -0.98
    ровая
    -0.97
    Holt
    -0.82
    әһ
    -0.81
     arch
    -0.81
     relentless
    -0.79
    médiaire
    -0.77
    Uris
    -0.77
    heten
    -0.76
    睐
    -0.76
    POSITIVE LOGITS
    ၇
    0.87
    ícia
    0.84
     millón
    0.84
    ishw
    0.82
    ify
    0.81
     Baş
    0.81
     Putih
    0.81
    umum
    0.81
    шит
    0.80
     bagus
    0.80
    Activations Density 0.162%

    No Known Activations