© 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. 234488
    Prev
    Next
    INDEX
    Explanations

    hailed as, travel insurance, May Zoo

    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
     Trường
    0.53
     Santos
    0.49
    Santos
    0.49
     Espírito
    0.48
     Роман
    0.46
     trám
    0.46
     substituir
    0.45
    守
    0.45
    撤
    0.45
     ని
    0.45
    POSITIVE LOGITS
     apprentice
    0.49
    passenger
    0.48
     wisata
    0.46
     Passengers
    0.46
    ophagy
    0.45
    predicate
    0.43
    ា
    0.43
    ྱ
    0.43
    catcher
    0.41
    anganese
    0.41
    Activations Density 0.002%

    No Known Activations