© 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. 49688
    Prev
    Next
    INDEX
    Explanations

    by company or employees

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

    Italian fiscal codes and identifiers

    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
    蓄
    0.46
     Colleen
    0.45
     Algorithm
    0.44
     Bianchi
    0.44
     collinear
    0.44
     plaintext
    0.43
     Greeting
    0.42
     km
    0.41
     Strategy
    0.41
     Kimmel
    0.41
    POSITIVE LOGITS
    łej
    0.53
    ܐ
    0.50
    łego
    0.50
    nelles
    0.48
    țională
    0.48
    ἢ
    0.48
    ły
    0.47
    
    0.47
    še
    0.46
    ła
    0.46
    Activations Density 0.000%

    No Known Activations