© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 31834
    Prev
    Next
    INDEX
    Explanations

    press release title, research

    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
    饷
    0.45
     Brunch
    0.42
    ランチ
    0.41
     потря
    0.40
    ård
    0.40
    芪
    0.40
     YoY
    0.39
    叕
    0.39
    িয়ে
    0.38
     карь
    0.38
    POSITIVE LOGITS
    Contacts
    0.45
     greenhouse
    0.40
     Carnegie
    0.40
    Institute
    0.39
    NASA
    0.39
    ###
    0.38
     contacts
    0.38
    Research
    0.38
     anu
    0.38
    Contact
    0.37
    Activations Density 0.000%

    No Known Activations