© 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. 1212
    Prev
    Next
    INDEX
    Explanations

    shapes, dimensions, positions

    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
     prepaid
    1.94
    UCLEAR
    1.84
    𝜇
    1.81
     incessantly
    1.75
     στον
    1.75
    soever
    1.74
     delas
    1.73
    წინ
    1.72
    िया
    1.70
    HIV
    1.69
    POSITIVE LOGITS
    ../
    1.70
    יא
    1.65
    yed
    1.65
    axia
    1.55
    ELY
    1.54
    edly
    1.54
    er
    1.54
    ing
    1.53
    ali
    1.53
    𝗸
    1.50
    Activations Density 0.212%

    No Known Activations