© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10412
    Prev
    Next
    INDEX
    Explanations

    dairy and milk

    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_262k_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
    𝘵
    2.51
    ר
    2.44
    ра
    2.44
    ان
    2.36
    ट
    2.35
     keer
    2.32
    ResourceManager
    2.24
    𝘳
    2.17
    ות
    2.16
    uig
    2.10
    POSITIVE LOGITS
    酪
    2.56
    inescent
    2.51
     sapply
    2.24
    ⃘
    2.22
    ள்ளன
    2.22
     того
    2.20
    ders
    2.19
     tomonidan
    2.17
     mañana
    2.14
     enfo
    2.12
    Activations Density 0.016%

    No Known Activations