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. 16-GEMMASCOPE-2-RES-262K
    4. 13851
    Prev
    Next
    INDEX
    Explanations

    another day or year

    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_16_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
    ।
    0.73
    _
    0.65
     <
    0.63
    :
    0.63
     divor
    0.59
     precursors
    0.58
    :
    0.57
    ²
    0.56
    ↵
    0.56
     whale
    0.56
    POSITIVE LOGITS
     Tattha
    0.72
     Тя
    0.60
    sunday
    0.58
     الجديدة
    0.57
     Ingeniería
    0.57
     счастли
    0.56
     নতুন
    0.56
     Vida
    0.56
     નવી
    0.55
    cpu
    0.55
    Activations Density 0.022%

    No Known Activations