© 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. 10-GEMMASCOPE-RES-131K
    7. 128195
    Prev
    Next
    INDEX
    Explanations

    has to be

    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
     jaja
    -1.81
     jesús
    -1.81
     to
    -1.71
     jajaja
    -1.66
     andando
    -1.66
     vernac
    -1.64
     andré
    -1.64
     bogotá
    -1.63
     peluche
    -1.63
     estadounid
    -1.60
    POSITIVE LOGITS
     поэтому
    1.75
    ↵
    1.65
     geeigne
    1.60
     ofreci
    1.52
     чувство
    1.52
     او
    1.48
    ↵↵
    1.48
    羸
    1.45
     assert
    1.41
     zweiter
    1.41
    Activations Density 0.017%

    No Known Activations