© 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. 31171
    Prev
    Next
    INDEX
    Explanations

    various languages

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

    applies, answer, remember, plugins

    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
    ೯
    0.46
     発
    0.45
     जिससे
    0.45
    峎
    0.44
    ೇವೆ
    0.44
    ើញ
    0.44
    ⇰
    0.44
    兴趣
    0.44
    伡
    0.43
     等
    0.43
    POSITIVE LOGITS
    ين
    0.49
     três
    0.48
    “
    0.46
     drie
    0.46
     Erinner
    0.46
     dwie
    0.46
    UCK
    0.45
     doua
    0.45
     baroque
    0.45
     Fraser
    0.44
    Activations Density 0.000%

    No Known Activations