© 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. 165174
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    Eb Dorian

    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
     omdat
    0.47
    मुझे
    0.47
     externa
    0.45
     надеюсь
    0.45
     เพราะ
    0.44
     рэгістра
    0.44
     因為
    0.44
     僕
    0.44
    because
    0.43
     eftersom
    0.43
    POSITIVE LOGITS
     enfon
    0.48
    各类
    0.47
     chiamato
    0.47
    شن
    0.47
    یت
    0.46
    Segoe
    0.45
    িন
    0.45
     لیاقت
    0.45
    ین
    0.44
    يت
    0.43
    Activations Density 0.001%

    No Known Activations