© 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
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4166
    Prev
    Next
    INDEX
    Explanations

    the phrase "i understand"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     privadas
    1.09
     Bravo
    1.07
    的には
    1.07
    ográficos
    1.07
    ура
    1.04
     miejsca
    1.03
    黾
    1.02
    she
    1.02
     специ
    1.01
     pessoais
    1.00
    POSITIVE LOGITS
    ration
    1.25
    ⅓
    1.19
     guess
    1.18
     home
    1.17
     length
    1.17
    φων
    1.16
     Bauhaus
    1.16
    beit
    1.14
    lfloor
    1.12
     illusion
    1.11
    Activations Density 0.052%

    No Known Activations