© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41336
    Prev
    Next
    INDEX
    Explanations

    depends what, deep dive, deep strategy

    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_31_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
     تحفظ
    0.47
     пище
    0.47
    িট
    0.45
    晹
    0.45
    েত্রে
    0.43
     लाइन
    0.43
    ipramine
    0.42
     কোটি
    0.42
     ম্যাগ
    0.42
     ঋণ
    0.42
    POSITIVE LOGITS
     recruit
    0.53
     trained
    0.48
     recruiter
    0.48
     officer
    0.48
     recruits
    0.48
     person
    0.48
    ↵↵
    0.47
     recruited
    0.46
     recruiting
    0.46
     officers
    0.46
    Activations Density 0.003%

    No Known Activations