© 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. 10451
    Prev
    Next
    INDEX
    Explanations

    geographic locations and associated entities

    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
     Versch
    1.88
     Одна
    1.80
    CIF
    1.75
    cstdlib
    1.74
     g
    1.74
     Begriff
    1.74
     kotlinx
    1.74
    Одна
    1.73
     fier
    1.73
     digestive
    1.71
    POSITIVE LOGITS
    ově
    2.15
    RE
    2.10
    цам
    2.08
    ዎቹ
    1.95
     nurtured
    1.91
    リ
    1.91
     nourished
    1.86
     ازيكم
    1.83
    沤
    1.82
    Acetic
    1.80
    Activations Density 0.178%

    No Known Activations