© 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. 90618
    Prev
    Next
    INDEX
    Explanations

    Van Gogh, metal alloys

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

    Van Gogh style, wheat field, red phosphorus

    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
     acidosis
    0.49
     acidification
    0.45
     sulfates
    0.44
    羧
    0.43
     microbial
    0.42
     Microbial
    0.42
     hydrolysis
    0.42
     inorganic
    0.42
     aqueous
    0.41
    的水
    0.41
    POSITIVE LOGITS
     என்றால்
    0.47
    API
    0.45
    焊
    0.43
     Antwerp
    0.42
    पै
    0.40
     Suriname
    0.39
    빛
    0.39
     Belgium
    0.39
     Palma
    0.39
    สวัสดี
    0.39
    Activations Density 0.047%

    No Known Activations