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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1352
    Prev
    Next
    INDEX
    Explanations

    AI tool names and phrases, model names

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

    the names of specific products, services, movies, games, or other proper nouns (named entities).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
    ቛ
    0.24
     !!,
    0.23
     keltiradi
    0.23
    segaretro
    0.22
    洶
    0.22
    وضع
    0.22
    譙
    0.22
    𝙡
    0.21
     يش
    0.21
    欝
    0.21
    POSITIVE LOGITS
    ’
    0.27
    0.22
    と呼ばれる
    0.21
    -
    0.21
    ·
    0.19
     mimics
    0.18
    '
    0.18
     ursprünglich
    0.17
     thậm
    0.17
    ならでは
    0.17
    Activations Density 0.592%

    No Known Activations