© 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. 163698
    Prev
    Next
    INDEX
    Explanations

    common application, risks, salt

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

    debt/equity, combined, on your

    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
    我
    0.53
    HOUSE
    0.52
    م
    0.51
    小屋
    0.50
    Over
    0.48
    ７
    0.48
    ozo
    0.47
    Request
    0.46
    毛
    0.46
     ماين
    0.46
    POSITIVE LOGITS
     katanya
    0.51
     ゆ
    0.50
     dimulai
    0.50
     adesso
    0.49
     उन्मूलन
    0.48
     said
    0.47
    िक्की
    0.47
    ș
    0.47
     पैदल
    0.47
     умови
    0.47
    Activations Density 0.001%

    No Known Activations