© 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-16K
    7. 2152
    Prev
    Next
    INDEX
    Explanations

    regex syntax elements

    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_16k_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
    нің
    1.30
    崙
    1.20
    \,\
    1.19
     ganger
    1.18
     pronouncing
    1.18
    ATION
    1.16
     heed
    1.14
    itores
    1.13
    ations
    1.10
    の頃
    1.07
    POSITIVE LOGITS
     siitä
    1.31
    platten
    1.21
    ます
    1.18
    Logout
    1.18
    ور
    1.16
    ong
    1.15
     خاصيه
    1.12
    ध
    1.12
     Esto
    1.11
    jat
    1.10
    Activations Density 0.005%

    No Known Activations