© 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. 10-GEMMASCOPE-RES-131K
    7. 41491
    Prev
    Next
    INDEX
    Explanations

    Operation client query

    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
    $
    -3.84
    From
    -3.59
    You
    -3.58
    Not
    -3.53
    Only
    -3.39
    Just
    -3.38
    If
    -3.30
    With
    -3.25
    When
    -3.25
    Your
    -3.23
    POSITIVE LOGITS
     are
    3.33
     다른
    2.92
    🫅
    2.78
    archiwizowane
    2.66
     fervent
    2.66
     testigos
    2.64
     dreary
    2.61
     terrific
    2.59
     astute
    2.56
     see
    2.55
    Activations Density 0.026%

    No Known Activations