© 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. 21284
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, or specific terms

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

    advanced solutions and statuses

    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
     акысыз
    0.48
     Hagg
    0.48
     啊
    0.48
    Hfn
    0.48
     समीप
    0.48
     कोणते
    0.47
     হেঁ
    0.47
     לג
    0.46
    ㄿ
    0.46
    uge
    0.46
    POSITIVE LOGITS
     Commissioner
    0.47
     the
    0.46
     License
    0.46
     Hindu
    0.46
     Thyroid
    0.45
    什么是
    0.44
    the
    0.43
     broken
    0.43
    ра
    0.42
     The
    0.42
    Activations Density 0.000%

    No Known Activations