© 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. 53-GEMMASCOPE-2-RES-262K
    7. 9493
    Prev
    Next
    INDEX
    Explanations

    numbers followed by commas or slashes

    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_53_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
    昃
    0.47
    зовая
    0.43
     renormalized
    0.41
    ＝＝
    0.41
     opposites
    0.37
     threx
    0.37
     Brownian
    0.35
    CATEG
    0.35
     تلوار
    0.35
    დომ
    0.35
    POSITIVE LOGITS
    শে
    0.71
    ″
    0.59
    esimo
    0.57
    世纪
    0.54
    ′
    0.50
    nd
    0.48
     कैरेट
    0.46
    ig
    0.46
    岁的
    0.46
    2
    0.45
    Activations Density 0.099%

    No Known Activations