© 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. 191572
    Prev
    Next
    INDEX
    Explanations

    land transfer, islands, blocks, height, process, needle, management

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

    AI hallucinations

    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
    atı
    0.48
    openhagen
    0.44
    斯
    0.44
    分开
    0.44
     육
    0.42
    leri
    0.42
    િંહ
    0.42
    plyr
    0.41
    茆
    0.41
    "。
    0.41
    POSITIVE LOGITS
     CSP
    0.47
    longmapsto
    0.46
     объема
    0.46
     enfin
    0.46
    wechsl
    0.45
     delivering
    0.45
     писал
    0.45
    żd
    0.44
     অন্তর্ভুক্ত
    0.44
     ;{
    0.44
    Activations Density 0.000%

    No Known Activations