© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84309
    Prev
    Next
    INDEX
    Explanations

    change and shift

    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
    hichever
    -1.05
    日発売
    -1.04
     atractivos
    -0.98
     continued
    -0.97
     still
    -0.95
    adhyay
    -0.93
    Grado
    -0.92
    現状
    -0.89
     mellett
    -0.88
    coef
    -0.88
    POSITIVE LOGITS
     to
    1.17
     changed
    1.10
     priorities
    1.09
     wherein
    1.06
     emphasis
    1.06
    quare
    1.02
     tzu
    1.01
    不再
    0.97
     حيث
    0.97
     chng
    0.96
    Activations Density 0.055%

    No Known Activations