© 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. 31605
    Prev
    Next
    INDEX
    Explanations

    multilingual context or lists

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

    "well" after a pause or low

    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
     Laird
    0.36
     (()
    0.36
     Тео
    0.35
    ↵
    0.35
          
    0.35
     Bo
    0.34
    ogin
    0.34
    urk
    0.34
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.34
            
    0.34
    POSITIVE LOGITS
    ībā
    0.45
     predominance
    0.41
    ihull
    0.41
     შეგი
    0.41
    maketitle
    0.40
    íme
    0.40
    די
    0.39
     tapaht
    0.39
     scholarship
    0.38
     disposer
    0.37
    Activations Density 0.003%

    No Known Activations