© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 27083
    Prev
    Next
    INDEX
    Explanations

    explaining relationships and context

    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_65k_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
    ettle
    0.50
     फुटबल
    0.50
    િટ
    0.49
    擎
    0.47
    神经
    0.47
    ilmiş
    0.47
     noirs
    0.47
    网址
    0.46
     deportivas
    0.46
    مک
    0.46
    POSITIVE LOGITS
     Gegen
    0.47
    j
    0.45
    ”（
    0.43
     Eben
    0.42
     contained
    0.42
     দাঁড়
    0.42
     IQR
    0.42
     clarifies
    0.42
     Obec
    0.41
     Unterstüt
    0.40
    Activations Density 0.011%

    No Known Activations