© 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. 22778
    Prev
    Next
    INDEX
    Explanations

    clenbuterol, limit texas, mcg

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

    producer-data, economic climate, suicide

    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
    ей
    0.48
    ня
    0.46
    ές
    0.46
    ప్పటికీ
    0.45
    нин
    0.45
    Pong
    0.44
    нути
    0.44
    D
    0.43
    Pad
    0.43
    ppins
    0.42
    POSITIVE LOGITS
     pulleys
    0.58
     स्विच
    0.52
     cinqui
    0.52
     এজ
    0.52
     shutters
    0.51
     balconies
    0.51
    ۵
    0.51
     turbines
    0.50
     frumo
    0.50
    illeurs
    0.50
    Activations Density 0.000%

    No Known Activations