© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3606
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by past tense verb

    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
     decency
    0.81
     gratification
    0.78
     satisfaction
    0.76
    代わりに
    0.73
     morals
    0.73
     reverting
    0.72
     compromise
    0.71
     }}">
    0.70
     ander
    0.70
     harmless
    0.68
    POSITIVE LOGITS
     vividly
    1.93
     fotografías
    1.85
    ircraft
    1.75
     зобра
    1.72
     décrit
    1.71
    śa
    1.71
    otipos
    1.70
    ongrass
    1.70
     نوع
    1.69
    baran
    1.69
    Activations Density 0.229%

    No Known Activations