© 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. 1937
    Prev
    Next
    INDEX
    Explanations

    list markers and markdown

    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
    ت
    1.28
    ی
    1.24
    ו
    1.24
    er
    1.23
    و
    1.20
    こと
    1.18
    ómo
    1.18
    ned
    1.14
    en
    1.14
    g
    1.13
    POSITIVE LOGITS
    CGPoint
    1.33
     pina
    1.32
     nanny
    1.25
    ј
    1.25
     follicles
    1.20
    .*
    1.18
    _*
    1.17
    𝗁
    1.16
     nourish
    1.16
    ️⃣
    1.15
    Activations Density 0.507%

    No Known Activations