© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 13864
    Prev
    Next
    INDEX
    Explanations

    dark evil or monstrous descriptions

    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_17_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
    ตรฐาน
    1.14
    tim
    1.13
    പ്പുറ
    1.11
    ter
    1.06
     {@
    1.06
    歴
    1.06
    تون
    1.05
    chang
    1.04
    spiel
    1.04
    li
    1.03
    POSITIVE LOGITS
    ু
    1.62
    ки
    1.35
    есть
    1.25
     ochron
    1.23
    ২
    1.23
    ढ
    1.22
     бре
    1.21
     doorbell
    1.20
     значит
    1.20
    म्मीद
    1.16
    Activations Density 0.008%

    No Known Activations