© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2750
    Prev
    Next
    INDEX
    Explanations

    one

    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
     первом
    -1.09
     eerste
    -1.09
     первого
    -1.06
     ibland
    -1.05
     ersten
    -1.05
     recientes
    -1.00
     первым
    -0.98
     hermosos
    -0.96
    пление
    -0.93
    ⌀
    -0.93
    POSITIVE LOGITS
     one
    6.22
    One
    2.72
     один
    2.63
    one
    2.56
    หนึ่ง
    2.55
     ONE
    2.47
     یکی
    2.44
     één
    2.42
     одну
    2.34
     yksi
    2.30
    Activations Density 0.039%

    No Known Activations