© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 17921
    Prev
    Next
    INDEX
    Explanations

    natural numbers

    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
    ма
    0.66
     ца
    0.62
     prosent
    0.62
    يا
    0.61
     operar
    0.61
    l
    0.60
    ла
    0.59
    antera
    0.59
    ш
    0.59
     sampe
    0.58
    POSITIVE LOGITS
     to
    0.71
    )
    0.70
     d
    0.67
    好的
    0.64
     easements
    0.64
     Africans
    0.63
     \
    0.63
     can
    0.63
     agreements
    0.62
     rigor
    0.61
    Activations Density 0.004%

    No Known Activations