© 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. 204864
    Prev
    Next
    INDEX
    Explanations

    useMemo, Bayes, connections

    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
    irmer
    0.40
     여기
    0.38
     ancho
    0.37
     conditioner
    0.37
    揪
    0.37
     cargar
    0.37
     encontraron
    0.37
    iye
    0.36
     rejuvenate
    0.34
     fanden
    0.34
    POSITIVE LOGITS
     अस्त
    0.41
     dem
    0.39
     canvas
    0.38
     sound
    0.38
    保留
    0.38
    瞄
    0.37
     подключения
    0.37
    URL
    0.36
    繋がり
    0.36
    ስቃሴ
    0.36
    Activations Density 0.015%

    No Known Activations