© 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. 11190
    Prev
    Next
    INDEX
    Explanations

    programming code and functions

    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
    ichier
    1.63
    ဖွဲ့
    1.54
    otiti
    1.54
    visibility
    1.53
    䜣
    1.48
    త్య
    1.48
     वाचा
    1.48
     technological
    1.45
    ◇
    1.45
    грама
    1.44
    POSITIVE LOGITS
     учре
    1.99
    ếu
    1.86
     kaçtır
    1.86
    as
    1.80
     увели
    1.78
    AsUp
    1.77
     Quant
    1.76
     consultato
    1.72
     engend
    1.71
     Poo
    1.70
    Activations Density 0.000%

    No Known Activations