© 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. 9-GEMMASCOPE-2-RES-16K
    4. 2081
    Prev
    Next
    INDEX
    Explanations

    unique identifiers and sequential numbers

    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
    ই
    3.04
    ר
    2.68
    至于
    2.66
    ز
    2.64
    可以看出
    2.61
    macosx
    2.59
    ل
    2.56
    ع
    2.55
    ல்
    2.55
    єю
    2.48
    POSITIVE LOGITS
    för
    2.46
    𝚊
    2.42
    formerly
    2.38
    ႈ
    2.30
     jsonObj
    2.27
     niektor
    2.25
     câteva
    2.20
    Omar
    2.20
     ktoré
    2.08
    ecie
    2.08
    Activations Density 0.132%

    No Known Activations