© 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. 1281
    Prev
    Next
    INDEX
    Explanations

    deaths, killed, assassinated

    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
    能
    1.37
     ello
    1.31
     recourse
    1.31
     entendido
    1.31
    ารย์
    1.22
     vostro
    1.21
    getStudentNo
    1.19
     podendo
    1.19
    л
    1.16
     agregado
    1.15
    POSITIVE LOGITS
    ح
    1.78
    ture
    1.47
    வ்வேறு
    1.37
    ⿲
    1.34
    asilkan
    1.29
     Suppose
    1.29
    ग्विजय
    1.27
     laurels
    1.25
     inaccuracies
    1.23
     borderRadius
    1.23
    Activations Density 0.118%

    No Known Activations