© 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. 71522
    Prev
    Next
    INDEX
    Explanations

    distinguishing languages

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

    searching specific terms

    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
    Events
    0.51
    *
    0.50
    Orden
    0.50
    Atl
    0.49
    Evento
    0.48
    App
    0.47
    Cuando
    0.47
    Vet
    0.47
    Eras
    0.47
    Ao
    0.46
    POSITIVE LOGITS
     गोली
    0.52
    睜
    0.49
    )。
    0.48
    股价
    0.48
     gonad
    0.47
     ด่า
    0.46
    TERN
    0.46
    σιν
    0.46
    ंग
    0.45
    umé
    0.45
    Activations Density 0.002%

    No Known Activations