© 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. 1648
    Prev
    Next
    INDEX
    Explanations

    enabling possibilities

    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
    𝐬
    4.35
    𝐀
    4.20
    𝐛
    3.80
    𝐩
    3.77
    𝐠
    3.66
    𝐂
    3.60
    𝐈
    3.49
    𝐁
    3.41
    𝐒
    3.38
    𝐌
    3.35
    POSITIVE LOGITS
    ات
    2.83
    ların
    2.61
     appl
    2.59
     избежать
    2.58
    थ
    2.57
    ές
    2.56
    melting
    2.52
    ają
    2.47
     동안
    2.46
    guien
    2.43
    Activations Density 0.573%

    No Known Activations