© 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. 162831
    Prev
    Next
    INDEX
    Explanations

    fastest Indian, under no, Japanese garden

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

    birthplace and housing status

    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
     Kennt
    0.49
     aras
    0.47
    ნ
    0.47
    ഃ
    0.47
    Sb
    0.46
    houn
    0.45
    orov
    0.44
     Cependant
    0.44
    ISupport
    0.44
    }\}$
    0.43
    POSITIVE LOGITS
     data
    0.51
     ransomware
    0.50
     overtaken
    0.47
     વખત
    0.47
     데이터
    0.46
     files
    0.46
     liabilities
    0.46
     outcomes
    0.45
     one
    0.45
     epochs
    0.44
    Activations Density 0.000%

    No Known Activations