© 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. 17-GEMMASCOPE-2-RES-16K
    7. 5348
    Prev
    Next
    INDEX
    Explanations

    numbered steps

    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_17_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
     lecz
    0.84
     few
    0.79
     去
    0.75
     或
    0.72
     emphasize
    0.70
     아니
    0.70
     아닌
    0.69
     তলায়
    0.68
     address
    0.68
    茲
    0.67
    POSITIVE LOGITS
     unconsciously
    0.67
    putes
    0.66
     गाइड
    0.66
     inconsc
    0.66
     পাঠান
    0.66
     ملا
    0.66
     receptors
    0.66
     télécharger
    0.65
    passenger
    0.65
    uyentes
    0.65
    Activations Density 0.030%

    No Known Activations