© 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. 33638
    Prev
    Next
    INDEX
    Explanations

    combination of

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

    text changes or error

    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
    arına
    0.49
    鴳
    0.49
    Frances
    0.48
     হয়েছিলেন
    0.48
    Ки
    0.47
    もあった
    0.46
    Жен
    0.46
    目は
    0.45
    ꞎ
    0.45
    홧
    0.45
    POSITIVE LOGITS
     ਸੁ
    0.46
     seu
    0.46
     be
    0.45
     մ
    0.45
     dėl
    0.44
     ზე
    0.44
     razor
    0.44
     ပြ
    0.43
     მოს
    0.43
     inducible
    0.43
    Activations Density 0.000%

    No Known Activations