© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 148373
    Prev
    Next
    INDEX
    Explanations

    without external compulsion or differentiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     expires
    0.77
     стихо
    0.73
     机
    0.71
     aż
    0.69
     सुनवाई
    0.69
     itulah
    0.68
     overshadow
    0.67
    ္ဂ
    0.66
     isotropic
    0.66
     имя
    0.66
    POSITIVE LOGITS
    クス
    0.79
     विज
    0.77
    ologists
    0.77
    রাস
    0.74
     বান্ধবী
    0.73
     readily
    0.72
    ).-
    0.72
    &-
    0.72
    ικές
    0.72
     możemy
    0.71
    Activations Density 0.001%

    No Known Activations