© 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. 172888
    Prev
    Next
    INDEX
    Explanations

    abide by

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

    gambling and technical terms

    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
    चुनाव
    0.43
    compact
    0.42
     الکتر
    0.41
    ৩৭
    0.40
     অধ্যাপক
    0.40
     имуще
    0.39
    \}$
    0.39
     ܀
    0.39
    startsWith
    0.39
     Dalib
    0.39
    POSITIVE LOGITS
    就已经
    0.52
     जाया
    0.47
    就被
    0.47
     stealing
    0.45
    而被
    0.44
    igning
    0.43
    就
    0.43
     coincident
    0.42
     meant
    0.42
    绯
    0.42
    Activations Density 0.000%

    No Known Activations