© 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. 157454
    Prev
    Next
    INDEX
    Explanations

    female athletes

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

    Emperor, president, RL, movement, questions, caused, elder

    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
    मेलन
    0.54
    מס
    0.46
     일반
    0.46
    优惠
    0.45
    לי
    0.45
    ני
    0.44
    挼
    0.44
    葆
    0.44
    не
    0.44
    Settl
    0.43
    POSITIVE LOGITS
     Lorentzian
    0.49
     was
    0.44
    EE
    0.44
    EU
    0.43
    }`))
    0.43
     arraigned
    0.42
     mutton
    0.41
     differed
    0.41
     portrays
    0.41
     presided
    0.40
    Activations Density 0.009%

    No Known Activations