© 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. 117387
    Prev
    Next
    INDEX
    Explanations

    clarification, clarity, explain

    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
     Rath
    -0.72
     mantener
    -0.72
     الولايات
    -0.71
     cambió
    -0.70
     배
    -0.70
    васто
    -0.69
    ⏪
    -0.69
    杵
    -0.69
    tillo
    -0.68
     Kame
    -0.68
    POSITIVE LOGITS
     clarity
    5.94
     Clarity
    4.16
    Clarity
    3.94
    clar
    3.84
     clarification
    3.59
     clarify
    3.55
     CLAR
    3.13
     claridad
    3.03
    CLAR
    2.94
     clarified
    2.86
    Activations Density 0.050%

    No Known Activations