© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 217036
    Prev
    Next
    INDEX
    Explanations

    countries and houses

    np_acts-logits-general · gemini-2.5-flash-lite

    order and sort results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     instante
    0.50
    ru
    0.47
    dueDate
    0.47
    test
    0.47
    的说
    0.46
    ></
    0.46
    )}}
    0.46
    ten
    0.46
    swering
    0.46
    teste
    0.46
    POSITIVE LOGITS
     Eurasian
    0.53
    unz
    0.46
     heer
    0.46
     पॉजिटिव
    0.46
     Celebrate
    0.46
    σιμοποι
    0.45
     manfaat
    0.44
     philanthropic
    0.44
    牪
    0.43
    泍
    0.42
    Activations Density 0.000%

    No Known Activations