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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7478
    Prev
    Next
    INDEX
    Explanations

    reporting events and consequences

    np_acts-logits-general · gemini-2.5-flash-lite

    requests and needs dialogue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    创造
    0.62
     உருவாக
    0.59
     potencialmente
    0.56
    线
    0.56
     உருவாக்கு
    0.56
     kullanılır
    0.55
    횽
    0.55
    定义
    0.54
     உலகின்
    0.54
     концеп
    0.53
    POSITIVE LOGITS
     আশ্বাস
    0.63
     dijeron
    0.61
     ambulances
    0.61
     told
    0.60
     ieri
    0.60
     জানিয়েছিলেন
    0.60
     電話
    0.59
    告知
    0.59
     yesterday
    0.58
     pleading
    0.58
    Activations Density 0.039%

    No Known Activations