© 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. 76631
    Prev
    Next
    INDEX
    Explanations

    if you or requirements

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

    United States

    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
    $)
    0.53
    thereum
    0.52
    ))
    0.52
    )【
    0.52
    )[
    0.50
    ?)
    0.50
    ),(
    0.50
     ?)
    0.49
    )?
    0.49
    )
    0.49
    POSITIVE LOGITS
    Innen
    0.43
    unky
    0.42
    六
    0.42
    だけでなく
    0.41
    सूचना
    0.41
    均
    0.41
     básicos
    0.41
    کین
    0.40
    اویر
    0.40
    arsk
    0.40
    Activations Density 0.001%

    No Known Activations