© 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. 100778
    Prev
    Next
    INDEX
    Explanations

    science and technical descriptors

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

    array named, time units, special characters

    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
     انت
    0.54
     बाती
    0.48
    of
    0.46
     ))
    0.45
    on
    0.45
     »
    0.45
     >
    0.43
    the
    0.43
     eff
    0.42
    ml
    0.42
    POSITIVE LOGITS
    Ě
    0.56
    ڃ
    0.52
    ჭირ
    0.48
     மாசுபடுத்த
    0.47
     član
    0.47
    ᚐ
    0.46
    }{$\
    0.44
    സമ
    0.44
    ()}\
    0.43
    ндарт
    0.43
    Activations Density 0.001%

    No Known Activations