© 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. 9663
    Prev
    Next
    INDEX
    Explanations

    San Diego

    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
    та
    1.44
    на
    1.19
    И
    1.19
    lerini
    1.11
    сі
    1.08
    ก
    1.07
    Ю
    1.06
    )$,
    1.05
    А
    1.02
    פ
    1.02
    POSITIVE LOGITS
    is
    1.67
    <0x80>
    1.16
    am
    1.14
    and
    1.02
    as
    1.01
     sd
    0.99
     almac
    0.99
    াতাড়ি
    0.98
    知道
    0.96
    是你
    0.95
    Activations Density 0.007%

    No Known Activations