© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2708
    Prev
    Next
    INDEX
    Explanations

    sentence endings and beginnings

    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_22_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
     idk
    1.34
    ｜
    1.10
    けど
    1.05
     แล้ว
    1.05
     不过
    1.02
     لكن
    1.02
    अगर
    1.01
    ጕ
    1.01
    ACIÓN
    1.01
    すごく
    1.01
    POSITIVE LOGITS
    또한
    1.25
     monies
    1.15
     또한
    1.14
     heretofore
    1.11
     denominada
    1.10
     विगत
    1.06
     данного
    1.05
     nuevamente
    1.05
     již
    1.04
     denominado
    1.01
    Activations Density 0.009%

    No Known Activations