© 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. 11739
    Prev
    Next
    INDEX
    Explanations

    start of code block

    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
    ه
    1.47
    MPI
    1.38
    dt
    1.30
    ř
    1.30
    നി
    1.29
    क
    1.29
    altitude
    1.27
    ی
    1.27
    اله
    1.26
    Rd
    1.26
    POSITIVE LOGITS
     pertenecen
    1.37
     bienvenidas
    1.36
     promover
    1.35
     barefoot
    1.28
     raping
    1.25
    ácil
    1.25
     મુજબ
    1.25
     là
    1.23
     của
    1.22
     turnkey
    1.22
    Activations Density 0.060%

    No Known Activations