© 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. 155357
    Prev
    Next
    INDEX
    Explanations

    `I` feel `sells` itself

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

    loan agreement

    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
    构
    0.49
     용
    0.45
    levation
    0.45
     fárm
    0.43
    Depth
    0.42
    IMPORT
    0.42
    维
    0.42
     것이
    0.41
     ಹೇ
    0.41
    弃
    0.41
    POSITIVE LOGITS
     pesquisas
    0.49
     halal
    0.48
     chatbots
    0.48
    yal
    0.46
     pesantren
    0.46
    utzen
    0.45
    ماش
    0.45
    patrick
    0.44
     буд
    0.43
     صاحب
    0.43
    Activations Density 0.001%

    No Known Activations