© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2329
    Prev
    Next
    INDEX
    Explanations

    introduce or Carl Philip

    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_9_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
    к
    3.84
    ا
    3.33
    ने
    3.20
     cuentan
    3.17
    ্স
    3.10
     mesmo
    3.03
    ла
    2.82
    зви
    2.82
    는
    2.78
    ed
    2.66
    POSITIVE LOGITS
    ম
    3.26
    𝑑
    3.24
    ingly
    3.07
    트워크
    2.97
    美元
    2.95
     vasomotor
    2.94
    是因为
    2.92
    Ꮼ
    2.89
    oze
    2.88
    יות
    2.81
    Activations Density 0.300%

    No Known Activations