© 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. 99332
    Prev
    Next
    INDEX
    Explanations

    systematic map

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

    definition and explanation headings

    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
     Poch
    0.47
     moder
    0.46
    ignant
    0.46
     Wisdom
    0.46
    Jour
    0.46
    届
    0.46
    注重
    0.43
    ╽
    0.43
    jav
    0.42
    Acces
    0.42
    POSITIVE LOGITS
     остальные
    0.50
     মজুদ
    0.46
     নগদ
    0.46
     द्रव्य
    0.45
     paralelas
    0.45
     enteros
    0.44
    小売
    0.44
     automóviles
    0.43
     unprofitable
    0.43
     வய
    0.43
    Activations Density 0.001%

    No Known Activations