© 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. 217238
    Prev
    Next
    INDEX
    Explanations

    discuss / instructions / hide / all / something / expand / under / rights / in / Leads

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

    of course combine

    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
     possíveis
    0.48
    我们要
    0.47
    山东
    0.47
     illa
    0.45
    上市公司
    0.45
    蒙
    0.45
    临
    0.44
    อน
    0.44
    行动
    0.43
    作者
    0.43
    POSITIVE LOGITS
    st
    0.54
    ost
    0.53
     alternately
    0.51
    বীর
    0.48
    ocer
    0.47
    carp
    0.47
     gradually
    0.47
    偵
    0.46
    troops
    0.46
    f
    0.46
    Activations Density 0.000%

    No Known Activations