© 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. 128098
    Prev
    Next
    INDEX
    Explanations

    legal and financial obligations

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

    SHA, RTX, FP, roots

    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
     کھل
    0.47
    房
    0.43
    wchar
    0.40
    第一
    0.39
    дир
    0.39
     diap
    0.37
    τισ
    0.37
    ハウス
    0.37
    是很
    0.37
    これからも
    0.37
    POSITIVE LOGITS
     invoices
    0.51
     callbacks
    0.50
    untut
    0.50
     obligations
    0.50
     निर्वा
    0.49
    _'.$
    0.49
     operand
    0.49
    öglichkeiten
    0.48
     proletariat
    0.48
     trabalhadores
    0.48
    Activations Density 0.002%

    No Known Activations