© 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. 43584
    Prev
    Next
    INDEX
    Explanations

    character encoding and decoding

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

    utf-8 encoding and decoding

    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
     विकलांग
    0.48
    کاری
    0.47
    adanam
    0.47
     appended
    0.46
    ים
    0.46
     inserted
    0.46
    ],
    0.46
    inisc
    0.44
     ,[
    0.44
    glyphicon
    0.43
    POSITIVE LOGITS
    StringEncoding
    0.49
     natür
    0.45
    來到
    0.44
    的多
    0.43
    rectionType
    0.43
    嚟
    0.42
     nyelv
    0.42
    俘
    0.42
     perlu
    0.41
    考虑到
    0.41
    Activations Density 0.001%

    No Known Activations