© 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. 103955
    Prev
    Next
    INDEX
    Explanations

    package.org

    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
    EDOM
    -0.78
     Muri
    -0.71
    gwick
    -0.70
     teleno
    -0.67
    DÉ
    -0.67
     нака
    -0.66
    vein
    -0.66
    તા
    -0.66
     Beatles
    -0.66
     beb
    -0.66
    POSITIVE LOGITS
    Paid
    0.88
     Paid
    0.86
    PAID
    0.83
    paid
    0.73
    ่ง
    0.73
     szükséges
    0.71
     Государ
    0.71
     Attachment
    0.71
    ør
    0.70
     paid
    0.69
    Activations Density 0.036%

    No Known Activations