© 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. 88287
    Prev
    Next
    INDEX
    Explanations

    countries, Italian, Chinese

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

    extracting data, flying, uploading

    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
    ête
    0.49
    ytail
    0.49
     ድ
    0.45
    ेंसी
    0.44
    eradish
    0.44
    ய்
    0.43
    abetes
    0.42
    〝
    0.41
     친
    0.41
     동시에
    0.41
    POSITIVE LOGITS
     acht
    0.50
     cinese
    0.50
     significativo
    0.48
     importante
    0.47
     potrebbe
    0.46
    在中国
    0.46
     significativa
    0.45
    中国
    0.44
    llr
    0.44
     semplic
    0.44
    Activations Density 0.000%

    No Known Activations