© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3046
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    Benzyloxy
    0.77
    ൊരു
    0.76
    ্র
    0.74
    Directive
    0.72
    ଢ
    0.66
    フィック
    0.65
    enarios
    0.65
    রামর্শ
    0.64
    बाजों
    0.64
    <unused62>
    0.64
    POSITIVE LOGITS
     while
    2.21
     regardless
    2.16
     despite
    2.08
     unless
    2.07
     whenever
    2.06
     during
    2.04
     whereas
    2.03
     whilst
    2.00
     without
    1.96
     because
    1.93
    Activations Density 1.225%

    No Known Activations