© 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. 181321
    Prev
    Next
    INDEX
    Explanations

    financial and descriptive contexts

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

    mathematical examples and concepts

    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
    戬
    0.50
    offensive
    0.46
    ও
    0.46
     сезона
    0.45
    进攻
    0.45
    盗
    0.45
    基本的に
    0.45
    Abstraction
    0.44
    পাঠ
    0.44
    未经
    0.44
    POSITIVE LOGITS
    ↵
    0.59
     drama
    0.53
     Drama
    0.50
     karar
    0.50
     ジャン
    0.50
     sette
    0.49
     domeni
    0.49
     Piero
    0.49
        
    0.48
     memilih
    0.48
    Activations Density 0.000%

    No Known Activations