© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13069
    Prev
    Next
    INDEX
    Explanations

    sports news links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     alcuna
    1.27
     psicologia
    1.27
     elegante
    1.27
     sottoline
    1.26
     sembra
    1.25
    <unused1412>
    1.25
     tBleStatus
    1.25
     vuccatiti
    1.24
    🔯
    1.23
    ꗚ
    1.23
    POSITIVE LOGITS
     journey
    1.04
    ↵
    0.91
    下
    0.85
     кор
    0.80
     snow
    0.79
     join
    0.78
     roots
    0.78
     Journey
    0.75
    ↵↵
    0.74
    0.74
    Activations Density 0.002%

    No Known Activations