© 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. 58607
    Prev
    Next
    INDEX
    Explanations

    your health or like I

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

    breakdown covering and

    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
    aranteed
    0.44
    Тех
    0.42
    炉
    0.41
    전히
    0.41
    rolet
    0.40
    各地
    0.39
    idade
    0.39
    нт
    0.39
    TNumber
    0.39
     manca
    0.39
    POSITIVE LOGITS
     потрібно
    0.53
     Jungkook
    0.52
     çant
    0.52
     Kardashian
    0.50
     Samba
    0.50
     échanges
    0.50
     exchanged
    0.49
     سٹ
    0.48
     ڪ
    0.48
     ချ
    0.48
    Activations Density 0.000%

    No Known Activations