© 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. 16-GEMMASCOPE-2-RES-262K
    7. 86622
    Prev
    Next
    INDEX
    Explanations

    like never before

    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
    pubescens
    0.64
    crates
    0.63
    ಿದರೆ
    0.61
    пример
    0.60
     экстре
    0.60
    firetruck
    0.59
    ຯ
    0.59
    softmax
    0.59
    thedocs
    0.59
    čku
    0.57
    POSITIVE LOGITS
     (
    0.86
     (“
    0.71
    ],”
    0.61
    s
    0.61
     ($\
    0.60
     supported
    0.56
     telah
    0.55
    ین
    0.55
     (‘
    0.55
     près
    0.54
    Activations Density 0.001%

    No Known Activations