© 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. 181028
    Prev
    Next
    INDEX
    Explanations

    before facing

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

    companies have documentation

    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
     Puch
    0.54
    »,
    0.50
     ,
    0.49
     К
    0.48
     Тя
    0.45
    Х
    0.44
    »:
    0.44
     gelangen
    0.43
     Pic
    0.43
     കാണ
    0.42
    POSITIVE LOGITS
     SAMPLE
    0.51
    葶
    0.48
    শিষ্ট
    0.47
    หมือน
    0.47
     spineItem
    0.46
    ினர்
    0.46
     নিয়োগ
    0.46
    োলন
    0.45
    ாமல்
    0.45
     köny
    0.44
    Activations Density 0.001%

    No Known Activations