© 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. 184397
    Prev
    Next
    INDEX
    Explanations

    line extending from

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

    uppercase to sentence

    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
     Jewelry
    0.50
     resur
    0.46
     &/
    0.46
    0.46
     бю
    0.45
     Affidavit
    0.44
     .
    0.43
     Bracelet
    0.43
     همد
    0.43
     =
    0.43
    POSITIVE LOGITS
    social
    0.48
    centres
    0.48
    विकास
    0.47
    ನ್
    0.46
    
    0.46
    𝓁
    0.45
    漃
    0.45
    ff
    0.44
     universidades
    0.44
     deportes
    0.44
    Activations Density 0.000%

    No Known Activations