© 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. 12681
    Prev
    Next
    INDEX
    Explanations

    since/sense of/we/the

    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
    ا
    3.65
    ب
    3.58
    ה
    3.36
    া
    3.24
     Certainly
    3.09
    a
    3.04
    ुक्त
    3.00
    ことが
    3.00
    ीण
    2.96
    to
    2.94
    POSITIVE LOGITS
    ح
    3.06
    ー
    2.93
    с
    2.92
    𝐧
    2.59
     potem
    2.57
    کار
    2.45
    ive
    2.45
    biggest
    2.43
    IZONTAL
    2.42
     luego
    2.38
    Activations Density 0.536%

    No Known Activations