© 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. 4528
    Prev
    Next
    INDEX
    Explanations

    rare or rarity

    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
     renormal
    1.07
    он
    1.02
    는
    0.92
    ход
    0.81
     deducted
    0.80
     decimated
    0.80
     несколь
    0.80
     владе
    0.77
    la
    0.77
     rubbed
    0.75
    POSITIVE LOGITS
    et
    1.61
    k
    1.29
    f
    1.28
    y
    1.18
    kep
    1.06
    er
    1.05
    z
    1.05
    ai
    1.04
    x
    1.04
    ari
    1.03
    Activations Density 0.015%

    No Known Activations