© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3176
    Prev
    Next
    INDEX
    Explanations

    shredded cheese

    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
     bb
    1.66
     p
    1.57
     fucking
    1.52
    ตู
    1.50
    ₍
    1.50
    碗
    1.46
     نفسك
    1.45
    朵
    1.44
     letra
    1.44
     Tiny
    1.43
    POSITIVE LOGITS
    eastern
    1.84
    Eastern
    1.83
    Intensity
    1.82
    frist
    1.69
    ய்ட
    1.64
     nécessité
    1.63
    淉
    1.63
    peripheral
    1.62
    鹂
    1.58
    incorpor
    1.57
    Activations Density 0.000%

    No Known Activations