© 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. 116957
    Prev
    Next
    INDEX
    Explanations

    taxpayers visit, chef masters

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

    humans and rules

    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
     thwart
    0.49
     इंस्पेक्टर
    0.44
    первых
    0.44
    ქვენ
    0.43
     funcionários
    0.43
    宁
    0.43
     površ
    0.42
     Isn
    0.42
    ውነተኛ
    0.42
     lét
    0.42
    POSITIVE LOGITS
    magnitude
    0.46
     accelerometer
    0.46
     calculator
    0.45
     calculators
    0.43
    λί
    0.42
    टि
    0.42
     britann
    0.41
    ரிக
    0.41
     অনেকেই
    0.40
    
    0.40
    Activations Density 0.001%

    No Known Activations