© 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. 109703
    Prev
    Next
    INDEX
    Explanations

    can make, but initially safe, they let

    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
     quadrat
    0.41
     eigenvectors
    0.39
    σ
    0.38
    蜱
    0.37
    тов
    0.37
    rient
    0.37
     composites
    0.37
    bius
    0.37
    蠍
    0.37
    ympt
    0.36
    POSITIVE LOGITS
    installment
    0.46
    ᾖ
    0.44
     இரா
    0.44
     отделения
    0.43
     Jiang
    0.42
     відді
    0.42
     Xinhua
    0.42
     nightlife
    0.42
     পরিষে
    0.41
     효
    0.41
    Activations Density 0.001%

    No Known Activations