© 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. 40560
    Prev
    Next
    INDEX
    Explanations

    sequence markers

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

    research, development, quotes

    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
    ==
    0.47
    =$
    0.47
    }=$
    0.46
    =${
    0.45
    是有
    0.45
     รอง
    0.44
    は
    0.44
    }=\
    0.44
    には
    0.44
    impan
    0.44
    POSITIVE LOGITS
     Yearbook
    0.50
     volna
    0.49
     Diary
    0.47
    ربعة
    0.46
     drei
    0.46
    نان
    0.44
     three
    0.44
    ظيف
    0.44
     dispuesto
    0.44
     molto
    0.43
    Activations Density 0.000%

    No Known Activations