© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9614
    Prev
    Next
    INDEX
    Explanations

    states of feeling

    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
    by
    1.33
    to
    1.25
    tain
    1.24
    the
    1.21
    s
    1.14
    asthen
    1.12
    é
    1.11
    groupBox
    1.09
    standing
    1.07
    lingu
    1.07
    POSITIVE LOGITS
    ة
    1.48
     microstructure
    1.38
    ري
    1.36
     hydrocarbon
    1.35
    本セット
    1.31
    kt
    1.29
     knots
    1.26
     Anschließend
    1.25
    েজ
    1.25
     обеспечивает
    1.24
    Activations Density 0.000%

    No Known Activations