© 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. 790
    Prev
    Next
    INDEX
    Explanations

    github.com and github.io

    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
     be
    0.18
    ig
    0.17
    2
    0.16
    4
    0.16
    ud
    0.14
    .’’
    0.14
    ков
    0.14
    я
    0.14
    EN
    0.13
    OLOGICAL
    0.13
    POSITIVE LOGITS
    0.20
    ت
    0.17
     cubierta
    0.16
    م
    0.15
     Einfluss
    0.15
     игровой
    0.15
    okkal
    0.15
     مكان
    0.14
    مكان
    0.14
     لأ
    0.14
    Activations Density 0.000%

    No Known Activations