© 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. 130925
    Prev
    Next
    INDEX
    Explanations

    languages or products

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

    evaluative contextsconcepts related to designcognitive shortcutscost and valuespecific topics or qualities

    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
    طات
    0.45
    مرة
    0.44
    이번
    0.43
    Hoch
    0.43
    果た
    0.41
    粖
    0.41
    容器
    0.40
    期間
    0.40
    తారు
    0.39
    قيم
    0.39
    POSITIVE LOGITS
     PDF
    0.52
     print
    0.52
     crumpled
    0.52
     printed
    0.51
     inkjet
    0.49
     pdf
    0.49
    lek
    0.49
     ruler
    0.49
     पीडीएफ
    0.48
     hole
    0.48
    Activations Density 0.000%

    No Known Activations