© 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. 224458
    Prev
    Next
    INDEX
    Explanations

    strength since

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

    understanding degrowth, antonyms, and specific places

    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
     독
    0.53
    lichting
    0.53
     furnishes
    0.48
    독
    0.48
     помещения
    0.47
     compresses
    0.46
    jän
    0.46
    꾀
    0.46
     것이
    0.46
     विमान
    0.46
    POSITIVE LOGITS
    ANDE
    0.52
    atchewan
    0.49
    ിക്കേണ്ട
    0.47
     tilted
    0.46
     presento
    0.46
     חיי
    0.46
     cuore
    0.46
    ன்
    0.45
     calcul
    0.45
     Montana
    0.44
    Activations Density 0.001%

    No Known Activations