© 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. 89039
    Prev
    Next
    INDEX
    Explanations

    facilitated manager damaged decorate

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

    business and commerce terms

    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
    າກ
    0.48
    酸化
    0.48
    Parking
    0.46
    ありません
    0.45
    钠
    0.45
    蝋
    0.42
    Humidity
    0.42
    cosity
    0.42
     ácidos
    0.42
    蔽
    0.42
    POSITIVE LOGITS
     interne
    0.57
     neurolog
    0.55
     alpin
    0.50
     intensiv
    0.50
     herunter
    0.47
    
    0.47
     selections
    0.46
     PACK
    0.46
    inis
    0.46
     المحلية
    0.46
    Activations Density 0.000%

    No Known Activations