© 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. 183936
    Prev
    Next
    INDEX
    Explanations

    her husband or partner

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

    international cooperation

    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
     transferência
    0.51
     orale
    0.51
    マ
    0.49
    丂
    0.47
     bactéries
    0.47
     gode
    0.46
     внутреннего
    0.46
     Ventilation
    0.46
    膂
    0.46
     depositions
    0.46
    POSITIVE LOGITS
    lingual
    0.45
    though
    0.44
    łącznie
    0.43
    ie
    0.42
     Републи
    0.41
     لوبی
    0.41
    ió
    0.41
    padx
    0.40
    יה
    0.40
    गारी
    0.40
    Activations Density 0.000%

    No Known Activations