© 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. 223205
    Prev
    Next
    INDEX
    Explanations

    multilingual consumers and nature

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

    physically leans in conspiratorially

    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
     المه
    0.53
     Spending
    0.49
    ج
    0.49
    гер
    0.47
    бель
    0.46
     сдела
    0.45
     вполне
    0.44
     منظم
    0.44
    á
    0.44
     месту
    0.43
    POSITIVE LOGITS
     konsumen
    0.55
     consumers
    0.54
     oceans
    0.50
    消費者
    0.49
     ISP
    0.48
     NTP
    0.48
     rooftops
    0.47
    🩶
    0.47
     dolphins
    0.47
     उपभोक्ताओं
    0.45
    Activations Density 0.003%

    No Known Activations