© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13684
    Prev
    Next
    INDEX
    Explanations

    transcranial magnetic or direct stimulation

    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
     smtp
    3.09
     atof
    3.07
     果
    3.07
    ROff
    3.05
    яза
    2.93
    ్రో
    2.93
    <unused1706>
    2.91
    owment
    2.88
     autorità
    2.87
     TabLayout
    2.87
    POSITIVE LOGITS
    er
    2.97
    ER
    2.47
    eram
    2.44
    候
    2.36
    ism
    2.30
    ter
    2.29
    燵
    2.25
    erden
    2.20
    ته
    2.16
    AR
    2.13
    Activations Density 0.003%

    No Known Activations