© 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. 6718
    Prev
    Next
    INDEX
    Explanations

    financial, historical, and numerical entities

    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
    阱
    1.02
     plent
    0.98
     preocupa
    0.98
    <unused2172>
    0.97
     nope
    0.96
     tble
    0.95
     poseen
    0.94
    ⏮
    0.94
     possède
    0.94
     rerum
    0.92
    POSITIVE LOGITS
    geführt
    1.04
    Så
    0.96
    歳の
    0.95
     Husband
    0.92
    mitted
    0.91
     झालेल्या
    0.90
     Kỳ
    0.89
     بين
    0.89
     Month
    0.89
     adaptés
    0.88
    Activations Density 0.077%

    No Known Activations