© 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. 223601
    Prev
    Next
    INDEX
    Explanations

    yoga and medical terms

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

    Outro)

    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
    with
    0.55
    ations
    0.52
    not
    0.47
    ะ
    0.46
    mets
    0.46
    nak
    0.45
    nos
    0.45
    nější
    0.45
    Av
    0.43
    辟
    0.42
    POSITIVE LOGITS
     beber
    0.52
    पणे
    0.52
     योग
    0.50
     યોગ
    0.50
     comprennent
    0.50
     içinde
    0.50
     diuretic
    0.49
     tattha
    0.48
    ERRORTYPE
    0.48
    EventManager
    0.47
    Activations Density 0.000%

    No Known Activations