© 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. 31-GEMMASCOPE-2-RES-262K
    7. 21021
    Prev
    Next
    INDEX
    Explanations

    yes, SFW

    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_31_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
     ರಚ
    0.43
    Kamol
    0.42
    [
    0.42
    𝓷
    0.41
    Huang
    0.41
    ্ডিং
    0.41
    tbLabel
    0.41
     Haaland
    0.40
    ilang
    0.40
     അതി
    0.40
    POSITIVE LOGITS
    at
    0.42
     Städ
    0.42
     eigenes
    0.42
    用
    0.42
    性
    0.41
    讓我們
    0.41
    加入
    0.40
    이
    0.40
     spielt
    0.40
     stro
    0.39
    Activations Density 0.000%

    No Known Activations