© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12210
    Prev
    Next
    INDEX
    Explanations

    software services and engineering

    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
    0.63
     сеть
    0.61
    ك
    0.61
    おり
    0.58
    กับ
    0.57
    lanır
    0.55
    ز
    0.55
    非常に
    0.54
    ために
    0.53
    зной
    0.53
    POSITIVE LOGITS
    Software
    1.52
     software
    1.34
     Software
    1.21
    software
    1.09
     सॉफ्टवेयर
    1.06
    软件
    1.05
     softwares
    1.02
    SOFTWARE
    0.97
    ソフトウェア
    0.95
    H
    0.91
    Activations Density 0.047%

    No Known Activations