© 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. 233723
    Prev
    Next
    INDEX
    Explanations

    multilingual indicators

    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
    徵
    0.48
    Ĝ
    0.46
     di
    0.45
     ())
    0.44
    pec
    0.44
    鑑
    0.43
     e
    0.43
    </code>
    0.42
     você
    0.42
    ﺖ
    0.41
    POSITIVE LOGITS
    섣
    0.49
     Wij
    0.49
    четов
    0.48
     Fleurit
    0.47
     विनोद
    0.47
     calendriers
    0.47
    눙
    0.46
     ಮಾರ
    0.46
    Wij
    0.45
    akkhati
    0.45
    Activations Density 0.000%

    No Known Activations