© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1690
    Prev
    Next
    INDEX
    Explanations

    news topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    веря
    1.88
     హైద
    1.86
    㚐
    1.80
    ￣
    1.77
    âmica
    1.74
    
    1.72
    এব
    1.71
    圿
    1.70
    粨
    1.70
    เกี่ยวข้อง
    1.69
    POSITIVE LOGITS
     sublicense
    1.82
     hätte
    1.70
     wäre
    1.65
    ත්තේ
    1.63
    णाला
    1.61
     sarebbe
    1.58
     olsa
    1.56
     conceivably
    1.55
     would
    1.52
     hypothetical
    1.52
    Activations Density 0.906%

    No Known Activations