© 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. 1373
    Prev
    Next
    INDEX
    Explanations

    every + unit or instance

    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
     for
    1.70
    يد
    1.34
    ี
    1.30
    is
    1.23
    ).
    1.15
    ),
    1.13
    ્
    1.11
    )
    1.09
    ó
    1.09
    ),"
    1.08
    POSITIVE LOGITS
    were
    1.11
    da
    1.09
    I
    1.07
    day
    1.06
    data
    1.06
    was
    1.06
    storey
    1.05
    name
    1.02
    test
    1.01
    that
    1.00
    Activations Density 0.022%

    No Known Activations