© 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. 246071
    Prev
    Next
    INDEX
    Explanations

    political figures

    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
    aniyati
    0.54
    ^{\
    0.50
    omp
    0.49
    ull
    0.49
    aris
    0.49
    ay
    0.48
    ann
    0.48
     និង
    0.47
    +\
    0.46
    ਤ
    0.46
    POSITIVE LOGITS
    团结
    0.51
    َاب
    0.49
    ,__
    0.45
     mecánico
    0.45
    কানিক্যাল
    0.44
    怨
    0.44
    ্থ
    0.44
    阃
    0.44
     COURT
    0.44
     backside
    0.43
    Activations Density 0.000%

    No Known Activations