© 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. 2344
    Prev
    Next
    INDEX
    Explanations

    be helpful

    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
    ดิน
    1.73
    倘
    1.71
    по
    1.64
     मद्देनजर
    1.62
    湎
    1.58
    lives
    1.54
     불구하고
    1.47
    <0xA1>
    1.46
    elem
    1.45
    hereafter
    1.44
    POSITIVE LOGITS
    nue
    2.06
    segaretro
    2.01
     libero
    1.97
    রিতে
    1.97
     capsid
    1.96
    ნენ
    1.93
    nk
    1.93
     parietal
    1.92
     ønsker
    1.90
    friend
    1.90
    Activations Density 0.130%

    No Known Activations