© 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. 40-GEMMASCOPE-2-RES-262K
    7. 28615
    Prev
    Next
    INDEX
    Explanations

    read more, eat dessert

    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_40_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
     सुनें
    0.44
    ڈی
    0.41
     cenderung
    0.39
     cuales
    0.39
     অনুসরণ
    0.38
     执行
    0.38
     pragmatic
    0.38
    뀜
    0.37
    纤维
    0.37
     सुनना
    0.36
    POSITIVE LOGITS
     more
    0.70
     also
    0.64
    More
    0.61
    also
    0.60
     também
    0.59
    more
    0.59
    También
    0.59
    también
    0.59
     next
    0.58
     también
    0.56
    Activations Density 0.000%

    No Known Activations