© 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. 13476
    Prev
    Next
    INDEX
    Explanations

    thought experiment

    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
    美元
    1.10
    amia
    1.09
    炜
    1.08
    jaan
    1.08
    wbr
    1.07
    raham
    1.05
    გი
    1.05
    aray
    1.03
    SECONDS
    1.02
    allax
    1.01
    POSITIVE LOGITS
     Pois
    1.31
     fungicides
    1.29
     להיות
    1.29
     केक
    1.27
     uk
    1.27
     reparto
    1.27
     넣
    1.26
     विष
    1.26
     Knowing
    1.26
     oxides
    1.24
    Activations Density 0.163%

    No Known Activations