© 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. 238476
    Prev
    Next
    INDEX
    Explanations

    historic city, Elvis Presley, tribal areas, Technical phase

    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
     cries
    0.55
     書き
    0.53
     あ
    0.52
     それぞれ
    0.50
     よく
    0.49
     な
    0.49
     女の子
    0.48
     ਇਹ
    0.48
     कहकर
    0.48
     ขึ้น
    0.48
    POSITIVE LOGITS
    רת
    0.48
    status
    0.46
     nitride
    0.45
    ري
    0.45
    ून
    0.44
    ్యాచ్
    0.44
    t
    0.44
     giảm
    0.43
    ва
    0.43
    ارة
    0.43
    Activations Density 0.000%

    No Known Activations