© 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. 165952
    Prev
    Next
    INDEX
    Explanations

    user input fields and data

    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
    熟
    0.44
    五个
    0.41
     idempotent
    0.40
     take
    0.37
    쪘
    0.37
    |^
    0.37
     sem
    0.36
    三人
    0.36
    ཉ
    0.36
     ਵਿ
    0.36
    POSITIVE LOGITS
    暝
    0.39
    Muhammad
    0.39
    льну
    0.39
    Format
    0.38
     zakon
    0.38
    atural
    0.37
    [multimodal]
    0.37
    νον
    0.36
    memor
    0.36
    olan
    0.36
    Activations Density 0.005%

    No Known Activations