© 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. 1784
    Prev
    Next
    INDEX
    Explanations

    small problems

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

    Chinese language, varieties, quarter

    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
    ﹋
    0.51
    憶
    0.50
    מ
    0.49
    面白い
    0.47
     resembles
    0.46
    ध्द
    0.46
    醜
    0.45
    សូម
    0.45
    いて
    0.45
    ॉल
    0.44
    POSITIVE LOGITS
     Seneca
    0.56
    kx
    0.50
    r
    0.48
    heiz
    0.47
     Taurus
    0.46
     PPP
    0.43
     negation
    0.43
     kurzen
    0.43
     kleinen
    0.43
     亀
    0.43
    Activations Density 0.000%

    No Known Activations