© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14116
    Prev
    Next
    INDEX
    Explanations

    only followed by a conditional

    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
    al
    2.52
    er
    2.51
    ו
    2.46
    و
    2.36
    u
    2.22
    Only
    2.08
    ю
    2.08
    ১
    2.03
    л
    2.03
    ful
    1.98
    POSITIVE LOGITS
    fans
    1.92
     méxico
    1.89
    큼
    1.88
     writ
    1.88
    想不到
    1.87
    Trashed
    1.87
     ótimo
    1.78
     bisa
    1.78
    𝙩
    1.77
    യി
    1.76
    Activations Density 0.094%

    No Known Activations