© 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. 126425
    Prev
    Next
    INDEX
    Explanations

    opponent's action or state

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

    absorption into, counter, divisible by, by the time

    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
    ן
    0.54
    ète
    0.50
     에너지
    0.50
     احتم
    0.50
     таблицу
    0.49
    utiérrez
    0.49
     jeweiligen
    0.49
    usetzen
    0.49
     테이블
    0.48
     탐
    0.48
    POSITIVE LOGITS
     we
    0.47
     atrib
    0.47
     vowel
    0.45
     system
    0.43
     renunci
    0.41
     is
    0.41
     safety
    0.40
    くちゃ
    0.40
     methods
    0.40
     cat
    0.40
    Activations Density 0.000%

    No Known Activations