© 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. 229106
    Prev
    Next
    INDEX
    Explanations

    artist website

    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
    chrom
    0.45
     була
    0.45
    ுக
    0.45
     ול
    0.45
     крю
    0.44
    contraction
    0.44
    encryption
    0.43
    ে
    0.43
    𝑦
    0.43
    Reco
    0.43
    POSITIVE LOGITS
    大陸
    0.49
    ਟੀ
    0.47
     Heterocycl
    0.46
    郅
    0.45
    ాత
    0.44
    勍
    0.44
    時候
    0.44
    只要
    0.44
    ્ર
    0.43
    两个
    0.43
    Activations Density 0.001%

    No Known Activations