© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 39982
    Prev
    Next
    INDEX
    Explanations

    opening, inauguration, launch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skú
    0.39
     volatility
    0.36
     fatig
    0.36
     portability
    0.36
     मात्रा
    0.35
     vocab
    0.35
     HOL
    0.35
     🤔
    0.35
     digestible
    0.34
    ڍ
    0.34
    POSITIVE LOGITS
     ceremon
    1.21
     ceremony
    1.20
     ceremonia
    1.16
     inaugur
    1.13
     ceremonies
    1.12
     Ceremony
    1.09
     inauguration
    1.09
    仪式
    1.08
     cerim
    1.07
     مراسم
    1.06
    Activations Density 0.013%

    No Known Activations