© 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. 197159
    Prev
    Next
    INDEX
    Explanations

    city names ending in ville

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

    collection of recipes

    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
    他們
    0.51
    峇
    0.48
    酈
    0.47
    ರ್
    0.46
     వారు
    0.45
     சுதந்திர
    0.44
    
    0.44
    地上
    0.43
     câu
    0.43
     Оде
    0.43
    POSITIVE LOGITS
    et
    0.51
    elman
    0.51
    i
    0.51
     nanny
    0.49
    enso
    0.47
    gres
    0.46
    enem
    0.46
     NPP
    0.46
     don
    0.46
    Large
    0.46
    Activations Density 0.000%

    No Known Activations