© 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. 44155
    Prev
    Next
    INDEX
    Explanations

    historical circumstances

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

    financial terms and calculations

    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
     Анастасия
    0.54
    Anast
    0.52
    Ана
    0.50
    
    0.50
    湍
    0.49
    onna
    0.49
    FirstFit
    0.49
    КА
    0.48
    婼
    0.48
    Finale
    0.47
    POSITIVE LOGITS
     municipal
    0.48
     cigarette
    0.48
     equities
    0.45
     par
    0.45
     buckle
    0.44
     meyd
    0.44
     gain
    0.44
     bond
    0.44
     retail
    0.44
     liquid
    0.44
    Activations Density 0.000%

    No Known Activations