© 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. 31-GEMMASCOPE-2-RES-262K
    7. 111474
    Prev
    Next
    INDEX
    Explanations

    systems, galaxy, biology

    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_31_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
    an
    0.53
    are
    0.50
    as
    0.44
     CPP
    0.43
    s
    0.43
    ن
    0.42
     saper
    0.41
    et
    0.41
     iman
    0.41
    z
    0.40
    POSITIVE LOGITS
    🧇
    0.50
    HttpDelete
    0.47
    ADOC
    0.47
    ীরা
    0.47
    🥙
    0.46
    HARAD
    0.46
    ﺍ
    0.46
    ເຮັດ
    0.45
    法施行令
    0.45
    केदार
    0.45
    Activations Density 0.001%

    No Known Activations