© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 109
    Prev
    Next
    INDEX
    Explanations

    model

    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_29_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
     now
    0.55
    izdat
    0.53
     اكتب
    0.53
    이제
    0.53
     trump
    0.53
    %\
    0.52
     poset
    0.52
     $<$
    0.52
    ष्टि
    0.51
    דת
    0.51
    POSITIVE LOGITS
    Жи
    0.45
    issy
    0.45
     Studies
    0.45
    rody
    0.44
    శా
    0.44
    قص
    0.44
    issa
    0.43
    かし
    0.43
    සා
    0.42
     Kapp
    0.42
    Activations Density 1.581%

    No Known Activations