© 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. 46425
    Prev
    Next
    INDEX
    Explanations

    Aurora as a name or place

    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
    i
    1.55
    ed
    1.43
    ي
    1.42
    e
    1.36
    ে
    1.29
    al
    1.27
    s
    1.27
    ”
    1.27
    é
    1.24
    ,
    1.22
    POSITIVE LOGITS
    на
    1.30
    𝒎
    1.24
    ﻣ
    1.16
    𝓽
    1.15
    ວ
    1.14
    𝑳
    1.14
     edificios
    1.09
    ﺳ
    1.09
    سی
    1.09
    𝚖
    1.09
    Activations Density 0.001%

    No Known Activations