© 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. 196520
    Prev
    Next
    INDEX
    Explanations

    sequencing methods, printing stock, she knows

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

    non-English numbers or units

    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
     butcher
    0.48
     turquoise
    0.46
     /ˈ
    0.45
     turístico
    0.44
     ic
    0.44
     tourism
    0.43
     pistachio
    0.42
     takePhotoButton
    0.42
     PX
    0.42
    的部分
    0.41
    POSITIVE LOGITS
     કરોડ
    0.55
    퐶
    0.50
    Debt
    0.49
    기가
    0.48
     অক্সিজেন
    0.47
    Ammo
    0.47
     миллионов
    0.46
     करोड़
    0.45
     trillions
    0.45
    亿
    0.45
    Activations Density 0.000%

    No Known Activations