© 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. 134658
    Prev
    Next
    INDEX
    Explanations

    lymphatic drainage

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

    program, code, names, or sourcing

    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
     &
    0.50
     fling
    0.50
     -
    0.47
    ere
    0.46
    \
    0.46
     oder
    0.45
     (
    0.45
     Apple
    0.44
     Copyright
    0.44
     file
    0.43
    POSITIVE LOGITS
     três
    0.51
    ཋ
    0.50
    があり
    0.49
    玛
    0.49
    沨
    0.49
    त्रि
    0.48
    ྭ
    0.48
    <0x8D>
    0.47
    ్రె
    0.47
    issantes
    0.47
    Activations Density 0.001%

    No Known Activations