© 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. 165462
    Prev
    Next
    INDEX
    Explanations

    awards and Muslims

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

    sesame seed buns

    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
     müssen
    0.50
     القرار
    0.48
     ženy
    0.45
     行
    0.45
    richtungen
    0.45
    透露
    0.44
     дані
    0.44
    らの
    0.44
     布
    0.44
    峇
    0.44
    POSITIVE LOGITS
    शा
    0.46
     Coloring
    0.45
    aia
    0.45
    XII
    0.45
    К
    0.45
    !
    0.45
    اسی
    0.44
    DA
    0.44
    CTV
    0.44
    ape
    0.44
    Activations Density 0.000%

    No Known Activations