© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5673
    Prev
    Next
    INDEX
    Explanations

    if __name__ == '__main__':

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
     karst
    0.94
     hasattr
    0.87
    Ding
    0.83
    рифт
    0.82
     얼마
    0.79
     graciously
    0.77
     cheesecake
    0.77
    媜
    0.77
    ℕ
    0.77
     bamboo
    0.76
    POSITIVE LOGITS
    وج
    0.74
     הרו
    0.71
    อง
    0.64
     दुस
    0.63
    染
    0.62
     উড়
    0.61
    血
    0.60
     blood
    0.59
    рави
    0.59
    見
    0.59
    Activations Density 0.006%

    No Known Activations