© 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. 10-GEMMASCOPE-RES-131K
    7. 69732
    Prev
    Next
    INDEX
    Explanations

    days of the week

    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
     Vielzahl
    -1.52
    为何
    -1.44
     you
    -1.29
    ourcen
    -1.24
     has
    -1.24
     
    -1.23
    vidade
    -1.23
     the
    -1.23
     amplia
    -1.22
     betyd
    -1.22
    POSITIVE LOGITS
    這是
    1.55
     tramont
    1.48
    ícone
    1.38
    vocations
    1.36
    This
    1.35
     utilizzando
    1.32
     فقط
    1.31
     nemmeno
    1.30
    kháu
    1.30
     даже
    1.28
    Activations Density 0.010%

    No Known Activations