© 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. 31118
    Prev
    Next
    INDEX
    Explanations

    giving or conveying to

    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
     upang
    -0.92
    和你
    -0.82
     нами
    -0.80
    هنگ
    -0.80
    jg
    -0.77
    和她
    -0.77
    让他
    -0.76
    让她
    -0.76
     незавершена
    -0.76
    让我
    -0.75
    POSITIVE LOGITS
     kepada
    3.88
    给
    2.95
    แก่
    2.50
    給
    2.50
     bagi
    2.23
    kepada
    2.19
     agli
    2.19
     aos
    2.16
     στους
    2.14
     unto
    2.08
    Activations Density 0.044%

    No Known Activations