© 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. 135188
    Prev
    Next
    INDEX
    Explanations

    new action

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

    ambitious but doable

    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
    anh
    0.52
    any
    0.46
    to
    0.43
     mankind
    0.43
    sud
    0.41
    chat
    0.41
    ི
    0.41
    Ironically
    0.40
    尘
    0.39
    tim
    0.38
    POSITIVE LOGITS
     ermöglicht
    0.56
     üç
    0.54
     AREA
    0.54
     ಸ್
    0.52
     ermöglichen
    0.52
     seç
    0.52
     CORE
    0.52
    嚩
    0.52
     YEAR
    0.51
     fornisce
    0.51
    Activations Density 0.000%

    No Known Activations