Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 2862
    Prev
    Next
    INDEX
    Explanations

    numbers and abbreviations

    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
    牪
    0.45
    رسٹ
    0.44
     বিভ
    0.39
    ovaniyu
    0.39
    پرس
    0.38
    ِلِّ
    0.38
    百万
    0.37
    ционной
    0.36
    یسم
    0.36
    criptive
    0.36
    POSITIVE LOGITS
    th
    0.80
    esimo
    0.53
    वीं
    0.52
    ″
    0.52
     మంది
    0.50
    ′
    0.48
     años
    0.45
     inches
    0.45
     years
    0.45
    yrs
    0.44
    Activations Density 0.153%

    No Known Activations