© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 205249
    Prev
    Next
    INDEX
    Explanations

    `extracts`, `makes models`, `dilation`

    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_40_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
     GPI
    0.41
     Анали
    0.41
     Compensation
    0.40
     расходов
    0.40
     $+
    0.40
     Fuzzy
    0.39
     bolso
    0.39
     Exchange
    0.39
     اختبار
    0.38
     Spy
    0.38
    POSITIVE LOGITS
    Tonight
    0.44
     Iman
    0.43
    Dise
    0.40
    িনায়ক
    0.40
    Es
    0.39
    ℑ
    0.39
    ikut
    0.38
    ineda
    0.38
    ިއ
    0.38
    Palest
    0.38
    Activations Density 0.000%

    No Known Activations