© 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. 244163
    Prev
    Next
    INDEX
    Explanations

    dependence on

    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
    Leaf
    0.48
    Hand
    0.48
    ItemList
    0.47
    ३
    0.47
    Mix
    0.46
     मिक्स
    0.45
    ૬
    0.45
     मल्टीप्लाई
    0.44
     میکس
    0.44
     Mix
    0.44
    POSITIVE LOGITS
     বিস্ম
    0.47
    గ్రహ
    0.46
    crollView
    0.46
    يدا
    0.45
     اعمال
    0.44
     أعمال
    0.43
     定
    0.43
    łego
    0.43
     থাক
    0.42
    自身
    0.42
    Activations Density 0.001%

    No Known Activations