© 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. 3167
    Prev
    Next
    INDEX
    Explanations

    Sal, Ad, Im, Pal, Bi, BL

    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_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
    <unused2123>
    1.20
    <unused2185>
    0.96
    <unused412>
    0.95
    <unused2136>
    0.95
     Loksatta
    0.94
    <unused2168>
    0.93
    <unused2109>
    0.92
     Trento
    0.92
     GitLab
    0.92
    <unused1038>
    0.91
    POSITIVE LOGITS
     Sch
    1.19
     Pe
    1.09
     El
    1.08
     Ver
    1.07
     आ
    1.01
     Re
    1.01
     Pro
    0.99
     Le
    0.96
     प्र
    0.94
     બ
    0.93
    Activations Density 2.419%

    No Known Activations