© 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. 173195
    Prev
    Next
    INDEX
    Explanations

    Wikipedia links to definitions

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

    code in unicode scripts

    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
     impasse
    0.39
     Sald
    0.37
     nuance
    0.36
    ₡
    0.36
    悸
    0.36
     Zuge
    0.36
     rupam
    0.35
     situational
    0.35
     particules
    0.35
     Fälle
    0.35
    POSITIVE LOGITS
     انگری
    0.38
    Dictionary
    0.37
     жана
    0.36
     เครื่อง
    0.35
     ২০১০
    0.34
     اسرائیل
    0.33
     ब्रिटेन
    0.33
     রাশিয়া
    0.33
    ("&
    0.33
     영어
    0.32
    Activations Density 0.000%

    No Known Activations