© 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. 133758
    Prev
    Next
    INDEX
    Explanations

    native components, chemical composition, visually distinct

    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
    ﻷ
    0.41
    MARY
    0.41
    𝜆
    0.41
    Mary
    0.40
    쏠
    0.39
    kami
    0.38
     Conti
    0.37
    ♾
    0.37
     roughly
    0.36
    러스
    0.36
    POSITIVE LOGITS
     belleza
    0.45
     торже
    0.43
     перед
    0.42
     Tongue
    0.42
     सुन्दर
    0.41
     अन्त
    0.41
     refuses
    0.40
    딴
    0.40
     آگے
    0.40
    দৃষ্টি
    0.40
    Activations Density 0.003%

    No Known Activations