© 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. 49135
    Prev
    Next
    INDEX
    Explanations

    able to, suitable for, arena shows

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

    Turkish, Indonesian, English

    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
    issement
    0.52
    منت
    0.50
    ዝና
    0.50
    ق
    0.49
    sticks
    0.48
    رف
    0.47
    rne
    0.47
    افت
    0.46
    رض
    0.46
     produire
    0.46
    POSITIVE LOGITS
     ancak
    0.47
    😰
    0.46
    😓
    0.44
    ↵
    0.43
     çocuk
    0.43
     penyebab
    0.43
     scolded
    0.43
     articulated
    0.42
    😭
    0.41
    😨
    0.41
    Activations Density 0.000%

    No Known Activations