© 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. 111043
    Prev
    Next
    INDEX
    Explanations

    discovery and its various applications

    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
     hidden
    0.42
     Fähigkeiten
    0.40
     фонбет
    0.39
     விருப்ப
    0.39
    webElement
    0.37
    능
    0.37
     instruções
    0.37
     инструкции
    0.37
    韫
    0.37
     Mün
    0.36
    POSITIVE LOGITS
    accessdate
    0.43
    cko
    0.43
    Discovery
    0.42
     telesc
    0.41
    Aprend
    0.40
    tls
    0.39
     estimados
    0.38
    yyyy
    0.38
    QUESTION
    0.36
    ্
    0.36
    Activations Density 0.006%

    No Known Activations