© 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. 243095
    Prev
    Next
    INDEX
    Explanations

    pay fordates or encountersradio show informationrespond to feedback

    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
     گوشی
    0.52
     wanting
    0.45
    ോള
    0.43
     хоте
    0.42
    饞
    0.42
    携帯
    0.41
     علامت
    0.41
    ಿಗ
    0.40
    嶼
    0.40
     относится
    0.40
    POSITIVE LOGITS
     Miles
    0.58
     ataupun
    0.56
     Shiva
    0.55
     Lila
    0.54
     Nirvana
    0.51
     Pand
    0.50
     Ric
    0.50
     Boca
    0.50
     James
    0.50
     Cairo
    0.50
    Activations Density 0.001%

    No Known Activations