© 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. 17554
    Prev
    Next
    INDEX
    Explanations

    marathon running

    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
    of
    1.17
    the
    1.15
    K
    0.91
    al
    0.91
    ofd
    0.90
    t
    0.89
    С
    0.89
    𝓭
    0.89
    Naive
    0.85
    tive
    0.84
    POSITIVE LOGITS
     marathon
    1.38
     Marathon
    1.24
     been
    1.13
    ?
    1.10
    ุ
    1.05
     l
    1.02
    ف
    1.00
     mar
    0.98
    ين
    0.97
     n
    0.91
    Activations Density 0.001%

    No Known Activations