© 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. 20861
    Prev
    Next
    INDEX
    Explanations

    React component class

    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
     декора
    0.49
     ẩm
    0.49
     дерев
    0.49
     использовали
    0.48
     координатами
    0.48
     режим
    0.47
     ассорти
    0.47
     ण
    0.46
     utilisé
    0.46
     использова
    0.45
    POSITIVE LOGITS
    Mys
    0.46
     inh
    0.43
     yeti
    0.43
     irrevers
    0.40
    mys
    0.40
    ”?
    0.39
    tc
    0.38
     মুখোমুখি
    0.38
    :+
    0.38
    bc
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.