© 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. 22-GEMMASCOPE-RES-131K
    7. 73258
    Prev
    Next
    INDEX
    Explanations

    identifying which or what

    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_22/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
    melse
    -0.95
    很多
    -0.87
    ถ้า
    -0.84
     ถ้า
    -0.84
    lagem
    -0.83
     tantos
    -0.83
    ucin
    -0.83
    ＞＞
    -0.83
     inclut
    -0.81
     }}">
    -0.79
    POSITIVE LOGITS
     each
    1.95
     certain
    1.44
     what
    1.37
     poszczegól
    1.32
     different
    1.18
    各个
    1.14
     particular
    1.13
     چه
    1.12
     how
    1.09
     لكل
    1.07
    Activations Density 0.056%

    No Known Activations