© 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. 1877
    Prev
    Next
    INDEX
    Explanations

    list/code formatting

    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
    ுகிற
    2.39
    𝘃
    2.27
    ্রো
    2.27
    ๅ
    2.24
     aceasta
    2.04
    ぅ
    2.03
     foams
    2.01
    ுகிறது
    1.97
     изобра
    1.92
     пищи
    1.92
    POSITIVE LOGITS
    ع
    3.29
    en
    2.68
    ので
    2.39
    ed
    2.15
    ال
    2.11
    ป์
    2.10
    maire
    2.02
    {},
    1.98
    bewerken
    1.94
    an
    1.94
    Activations Density 0.295%

    No Known Activations