© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 13062
    Prev
    Next
    INDEX
    Explanations

    i can or want to

    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_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
     resounding
    0.86
    儷
    0.84
    ﻟ
    0.84
     unequivocally
    0.83
     raccolta
    0.79
     ਪ੍ਰ
    0.79
     حکم
    0.79
     સમગ્ર
    0.78
     ﺍ
    0.78
     erupted
    0.78
    POSITIVE LOGITS
    also
    1.40
    ちなみに
    1.31
    Also
    1.29
     also
    1.28
     همچنین
    1.25
     Also
    1.23
     также
    1.23
    también
    1.21
     también
    1.17
     також
    1.10
    Activations Density 0.081%

    No Known Activations