© 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. 149377
    Prev
    Next
    INDEX
    Explanations

    'ca' or 'ta' syllable words

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

    international shipments

    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
    ار
    0.55
    ل
    0.53
    ።
    0.51
    いくつか
    0.49
    。。
    0.48
     。
    0.47
     monitoring
    0.47
    到
    0.47
    G
    0.47
     TR
    0.46
    POSITIVE LOGITS
    cada
    0.52
    cana
    0.52
     শাখা
    0.49
    cabin
    0.49
    tach
    0.49
    pwd
    0.48
    zado
    0.48
    zco
    0.48
    tan
    0.47
    pore
    0.47
    Activations Density 0.002%

    No Known Activations