© 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. 168194
    Prev
    Next
    INDEX
    Explanations

    specific origins or related concepts

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

    partially abbreviated or modified words

    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
    ģ
    0.48
    Gaz
    0.40
    谨慎
    0.40
    ح
    0.39
     tercero
    0.38
    ս
    0.38
     upgrades
    0.38
    现实
    0.38
    today
    0.38
    滥
    0.37
    POSITIVE LOGITS
     問
    0.54
    電荷
    0.53
     शुक्
    0.50
     மேற்பர
    0.50
     wrinkled
    0.50
     書い
    0.49
     ferrite
    0.48
     exfol
    0.48
    臨界
    0.48
     senhor
    0.47
    Activations Density 0.000%

    No Known Activations