© 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. 41897
    Prev
    Next
    INDEX
    Explanations

    Stop Soros act initiatives

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

    instructions for building or planning

    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
    ed
    0.51
    r
    0.49
    p
    0.49
    rs
    0.46
     during
    0.45
    certified
    0.45
    dt
    0.43
    ch
    0.43
    t
    0.43
    et
    0.43
    POSITIVE LOGITS
     궁
    0.55
    硙
    0.53
    ProductsStore
    0.50
    కునే
    0.49
    甪
    0.49
     marginLeft
    0.49
     노력
    0.49
     누구
    0.48
     기본
    0.48
     페이지
    0.48
    Activations Density 0.000%

    No Known Activations