© 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. 9721
    Prev
    Next
    INDEX
    Explanations

    religion or commands

    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
    ши
    1.36
    त्ते
    1.23
    tio
    1.23
     proiect
    1.22
    са
    1.17
     respectiv
    1.16
     suyo
    1.16
    !}{
    1.15
    ر
    1.15
    িলের
    1.13
    POSITIVE LOGITS
    stateMutability
    1.57
    വ്
    1.43
     indulged
    1.40
    นั่ง
    1.35
    withstanding
    1.35
    וש
    1.24
    på
    1.23
    bangan
    1.22
    mylist
    1.20
    হোক
    1.20
    Activations Density 0.000%

    No Known Activations