© 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. 34-GEMMASCOPE-RES-131K
    7. 65668
    Prev
    Next
    INDEX
    Explanations

    counting occurrences

    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
    ﾞ
    -0.77
    noteq
    -0.71
    кация
    -0.71
    🛂
    -0.69
     inaugurated
    -0.68
    πον
    -0.66
    pfung
    -0.66
    laszt
    -0.65
     вариантов
    -0.65
     projectiles
    -0.65
    POSITIVE LOGITS
     occurrence
    5.81
     occurrences
    4.97
    occurrence
    4.50
     Occurrence
    4.38
     occur
    4.34
    Occurrence
    4.19
     occ
    4.09
     Occur
    3.89
     occurring
    3.88
    occur
    3.88
    Activations Density 0.272%

    No Known Activations