© 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. 10379
    Prev
    Next
    INDEX
    Explanations

    high cheekbones

    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
    ل
    3.41
    ва
    3.28
    ל
    2.87
    ब
    2.85
    ১
    2.85
    رة
    2.81
    вање
    2.79
    ن
    2.72
    ли
    2.65
    نم
    2.60
    POSITIVE LOGITS
    addSubview
    2.51
    tmux
    2.50
    которые
    2.42
     nacido
    2.42
    stitches
    2.39
    ‖</
    2.39
     MediaQuery
    2.38
    timestamp
    2.30
    ulares
    2.26
    ensão
    2.24
    Activations Density 0.017%

    No Known Activations