© 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. 31-GEMMASCOPE-2-RES-262K
    4. 12652
    Prev
    Next
    INDEX
    Explanations

    condition, issues, accessories

    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
     auctions
    0.44
     auction
    0.44
     antique
    0.42
     antiques
    0.42
     Auctions
    0.38
     acquisitions
    0.37
    拝
    0.36
     ორ
    0.36
     stumpage
    0.35
     লেন
    0.35
    POSITIVE LOGITS
    astikan
    0.47
    жалуйста
    0.45
    ჰ
    0.42
    ütfen
    0.41
     garantire
    0.40
    гласно
    0.40
    ята
    0.40
    Vegan
    0.40
    ewnątrz
    0.40
     yana
    0.40
    Activations Density 0.005%

    No Known Activations