© 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. 111600
    Prev
    Next
    INDEX
    Explanations

    general elements

    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
     дости
    0.47
     출력
    0.45
     기초
    0.44
     만족
    0.44
    ጿ
    0.44
    Produkt
    0.42
    ጇ
    0.42
     전류
    0.42
    出力
    0.42
     각각
    0.42
    POSITIVE LOGITS
     carbonic
    0.52
     wheel
    0.50
     abdom
    0.50
    </h2>
    0.50
     kidneys
    0.48
     corpse
    0.48
     Everest
    0.48
     unconventional
    0.47
     ankle
    0.47
     gestational
    0.47
    Activations Density 0.003%

    No Known Activations