© 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. 30601
    Prev
    Next
    INDEX
    Explanations

    packet-switched data collection

    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
    การ
    0.41
    ᆷ
    0.40
    ření
    0.39
    学校
    0.39
    テー
    0.38
    ョ
    0.38
    |+\
    0.38
    ificazione
    0.37
     opposit
    0.37
    畲
    0.37
    POSITIVE LOGITS
     decimal
    0.44
     dew
    0.39
    drops
    0.38
    wik
    0.37
     explicado
    0.37
    Dew
    0.37
     spust
    0.37
     बाला
    0.36
    decimal
    0.36
    etah
    0.35
    Activations Density 0.000%

    No Known Activations