© 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. 84443
    Prev
    Next
    INDEX
    Explanations

    activities and time

    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
    含有
    0.51
    ਂ
    0.42
    뷰
    0.41
     sharps
    0.41
     проєкту
    0.41
    ezas
    0.40
     sadr
    0.40
     primitive
    0.39
    ﻲ
    0.38
    ᄏ
    0.38
    POSITIVE LOGITS
     onerous
    0.41
    Kiev
    0.41
     Париж
    0.41
     неде
    0.40
     зимой
    0.40
    Activities
    0.39
     ACTIVITIES
    0.39
     ఆదాయ
    0.39
    shopping
    0.38
    Pets
    0.38
    Activations Density 0.003%

    No Known Activations