© 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. 40-GEMMASCOPE-2-RES-262K
    7. 110623
    Prev
    Next
    INDEX
    Explanations

    traffic higher

    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_40_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
     chicos
    0.38
    販売
    0.37
     multiplicación
    0.37
     страниц
    0.37
    扱い
    0.36
    uks
    0.36
    Satellite
    0.36
    辦
    0.36
     বৃত্তি
    0.35
    岬
    0.35
    POSITIVE LOGITS
     strut
    0.39
     நோ
    0.38
     ṣe
    0.38
     WEL
    0.38
     Fer
    0.37
    зер
    0.37
     html
    0.37
     niobium
    0.36
    ckie
    0.36
     NB
    0.36
    Activations Density 0.000%

    No Known Activations