© 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. 86564
    Prev
    Next
    INDEX
    Explanations

    pertaining to

    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
    s
    1.48
    b
    1.29
    de
    1.17
    t
    1.12
    et
    1.10
     by
    1.09
    d
    1.09
    y
    1.08
    en
    1.06
     for
    1.00
    POSITIVE LOGITS
    )。
    1.16
    )，
    0.91
    }).
    0.86
    ).
    0.84
     can
    0.84
    та
    0.83
     ouvr
    0.82
    ти
    0.82
    ）。
    0.82
    文件
    0.81
    Activations Density 0.002%

    No Known Activations