© 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-262K
    7. 10724
    Prev
    Next
    INDEX
    Explanations

    of two people

    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
    catalog
    1.51
    er
    1.46
    cza
    1.46
    い
    1.46
    রত
    1.42
     véritables
    1.41
    ्यूब
    1.41
     entitle
    1.41
     넓
    1.37
     jurors
    1.37
    POSITIVE LOGITS
    是为了
    1.40
    是因為
    1.37
    是因为
    1.33
     इसलिए
    1.27
    ТИ
    1.26
    ന്ന്
    1.24
     Перед
    1.24
    是
    1.23
    是被
    1.22
    inception
    1.21
    Activations Density 0.000%

    No Known Activations