© 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. 12340
    Prev
    Next
    INDEX
    Explanations

    opinions expressed

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

    views expressed

    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
     trusty
    0.45
    engines
    0.45
     zwar
    0.44
    ਗਾ
    0.43
    を使って
    0.43
     Rupees
    0.43
    ###############
    0.43
     insgesamt
    0.42
    ##############
    0.42
     submarines
    0.41
    POSITIVE LOGITS
    钛
    0.51
    颈
    0.48
    绾
    0.47
    董事长
    0.46
    该公司
    0.46
    න්
    0.46
    在这
    0.46
    劏
    0.45
    在一个
    0.45
    促销
    0.45
    Activations Density 0.000%

    No Known Activations