© 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. 138116
    Prev
    Next
    INDEX
    Explanations

    quantities followed by units or descriptors

    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
    )
    0.56
    ﻼ
    0.50
     besoins
    0.48
    needs
    0.47
     고객
    0.46
     clienti
    0.46
     façons
    0.45
     stesse
    0.45
    umpang
    0.45
    ⵄ
    0.45
    POSITIVE LOGITS
     Tuberculosis
    0.54
     glacier
    0.51
     प्रीवियस
    0.49
     Arithmetic
    0.48
     युद्ध
    0.48
    ាល់
    0.48
    !.
    0.47
    ﹀
    0.47
    ిన
    0.46
     Numpy
    0.46
    Activations Density 0.001%

    No Known Activations