© 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. 111543
    Prev
    Next
    INDEX
    Explanations

    these things, numbers, prices

    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
     exercício
    0.42
     cheesy
    0.42
     니
    0.38
     गाँधी
    0.38
    नी
    0.37
     jasmine
    0.37
     repeatedly
    0.36
     discussion
    0.36
     मामूली
    0.36
     barbeque
    0.36
    POSITIVE LOGITS
    见了
    0.42
     없습니다
    0.40
    tails
    0.40
     unterstützt
    0.39
    双
    0.38
    ringar
    0.38
     geliş
    0.38
    protect
    0.38
    sik
    0.38
    ultaneous
    0.37
    Activations Density 0.000%

    No Known Activations