Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 5941
    Prev
    Next
    INDEX
    Explanations

    More followed by qualifiers

    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
    ۔
    1.54
    are
    1.49
    ।
    1.38
    เป็น
    1.38
    ,
    1.29
    는
    1.29
     arrhythmias
    1.25
    0
    1.20
    ك
    1.17
    ،
    1.13
    POSITIVE LOGITS
    (
    1.48
    t
    1.45
    на
    1.41
    ли
    1.28
    <0x80>
    1.16
    ية
    1.10
    h
    1.10
    ல்
    1.09
    ﺲ
    1.09
    舩
    1.04
    Activations Density 0.344%

    No Known Activations