© 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. 2321
    Prev
    Next
    INDEX
    Explanations

    July Fourth and CSS display

    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
    sik
    1.52
    iune
    1.43
    larni
    1.38
    soluble
    1.34
    ∎
    1.30
    agro
    1.29
    icii
    1.25
    ions
    1.23
    िल्‍ली
    1.22
     ina
    1.22
    POSITIVE LOGITS
     troca
    1.30
     guarantee
    1.28
    是
    1.27
    приклад
    1.27
    о
    1.26
    б
    1.24
     rechts
    1.23
     consigue
    1.23
    ্র
    1.22
    gewicht
    1.21
    Activations Density 0.016%

    No Known Activations