© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2199
    Prev
    Next
    INDEX
    Explanations

    middle class, Middle East, Middle Ages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
     demandé
    0.99
    参赛
    0.97
    咕
    0.94
     zabezpie
    0.90
    atip
    0.84
    spir
    0.84
    íč
    0.82
     certiorari
    0.81
     vaginalis
    0.79
    제
    0.79
    POSITIVE LOGITS
     Ages
    1.93
     районов
    1.90
    间的
    1.86
    란드
    1.84
    vania
    1.84
    чники
    1.83
     степени
    1.83
     tarde
    1.80
    чника
    1.75
    iscale
    1.74
    Activations Density 0.124%

    No Known Activations