© 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. 174304
    Prev
    Next
    INDEX
    Explanations

    words in

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

    past purchases, annual revenue, annualized returns, formerly performed, handle heavier, smart home

    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
     Pé
    0.51
     recharged
    0.49
     Pythag
    0.48
    ἥ
    0.47
     Pythagorean
    0.46
     cassava
    0.46
     那
    0.45
     uplifting
    0.45
     conséquence
    0.45
     És
    0.44
    POSITIVE LOGITS
    ک
    0.54
    ंटर
    0.51
    کو
    0.47
    िज
    0.45
    directed
    0.44
    scope
    0.43
    सारी
    0.43
    mmm
    0.43
    ویزی
    0.43
     گھر
    0.42
    Activations Density 0.002%

    No Known Activations