© 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. 51314
    Prev
    Next
    INDEX
    Explanations

    motion and progress

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

    sorting lists and items

    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
     যদি
    0.50
    ྲ
    0.47
     भोग
    0.46
     रक्षाबंधनाच्या
    0.45
     चाहि
    0.45
     ईरानी
    0.45
     अंसारी
    0.45
    😭😭
    0.44
     карты
    0.44
     शादी
    0.42
    POSITIVE LOGITS
     initially
    0.49
     laterally
    0.46
     pedagog
    0.46
     errone
    0.45
     diagnost
    0.44
    Initially
    0.44
     pedagogical
    0.43
     overtly
    0.43
     replete
    0.43
     unmittelbar
    0.43
    Activations Density 0.000%

    No Known Activations