© 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. 23099
    Prev
    Next
    INDEX
    Explanations

    locations and numerical identifiers

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

    code examples and definitions

    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
    ifying
    0.35
    ification
    0.34
    েন্দ্রলাল
    0.34
     কারণেই
    0.33
    7
    0.33
    5
    0.32
    এই
    0.31
    )))
    0.31
    iriya
    0.31
     whereupon
    0.30
    POSITIVE LOGITS
    出来る
    0.36
    രെ
    0.35
     duniya
    0.35
     イメージ
    0.35
    깆
    0.35
     također
    0.35
     соответствующие
    0.35
    ερ
    0.34
     دا
    0.34
     да
    0.34
    Activations Density 0.006%

    No Known Activations