© 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. 102205
    Prev
    Next
    INDEX
    Explanations

    high commission

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

    Whispering + natural feature

    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
    n
    0.52
    न
    0.52
    ع
    0.50
     Są
    0.46
     Michaelmas
    0.46
    mma
    0.45
     नेतृत्व
    0.44
     Britann
    0.44
    나
    0.44
    任何人
    0.44
    POSITIVE LOGITS
    ashita
    0.47
     usc
    0.46
     unsupervised
    0.46
     নিয়েছে
    0.45
     নিচ্ছে
    0.45
    🗯
    0.45
    渽
    0.45
     giud
    0.44
     entschied
    0.44
     carcin
    0.44
    Activations Density 0.000%

    No Known Activations