© 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. 40-GEMMASCOPE-2-RES-262K
    7. 134018
    Prev
    Next
    INDEX
    Explanations

    greeting, character, numerals, settings, array

    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
    rodite
    0.42
     PW
    0.40
     Mu
    0.39
    䪲
    0.39
    oss
    0.39
     CW
    0.38
    閩
    0.38
     Molecular
    0.38
    controller
    0.38
     Mir
    0.38
    POSITIVE LOGITS
     స్థ
    0.43
    吃饭
    0.41
     설정
    0.39
    ayvachi
    0.39
     설
    0.39
     inevitably
    0.39
     مقامی
    0.39
     এলাক
    0.38
    前辈
    0.38
     inev
    0.38
    Activations Density 0.001%

    No Known Activations