© 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. 182053
    Prev
    Next
    INDEX
    Explanations

    economic activity

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

    street food

    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
     przem
    0.60
    聝
    0.56
     ਤ
    0.53
    伌
    0.50
     பணிய
    0.50
     કાર્ય
    0.50
    聁
    0.49
    躹
    0.49
     ਨ
    0.49
     nég
    0.49
    POSITIVE LOGITS
    at
    0.52
     timings
    0.44
     biota
    0.42
    O
    0.42
     ہوسک
    0.41
    ↵
    0.41
    रसा
    0.41
     samoglas
    0.40
     timing
    0.39
     loci
    0.39
    Activations Density 0.000%

    No Known Activations