© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 33993
    Prev
    Next
    INDEX
    Explanations

    partial derivatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     पढ़ा
    0.46
    LiveData
    0.40
     प्रथा
    0.39
    𝕂
    0.39
     นิ
    0.39
     皮
    0.38
    IsNot
    0.38
     聞い
    0.38
     ساخت
    0.38
     กร
    0.38
    POSITIVE LOGITS
    /∂
    0.51
    t
    0.45
     thrown
    0.43
     stuffed
    0.43
    u
    0.42
    ')['
    0.41
     Autos
    0.40
     snaps
    0.38
     backs
    0.38
     bumper
    0.38
    Activations Density 0.001%

    No Known Activations