© 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-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 158
    Prev
    Next
    INDEX
    Explanations

    It's important

    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
    orschung
    1.38
    在新
    1.34
     Kyi
    1.33
    我们在
    1.29
    fisher
    1.25
     Kir
    1.21
    鵠
    1.21
     Vard
    1.21
     legislature
    1.20
    ぞれ
    1.20
    POSITIVE LOGITS
    inerary
    1.84
    INER
    1.40
     rained
    1.38
    <unused2223>
    1.36
     beho
    1.31
     fallait
    1.24
    alic
    1.23
     viktigt
    1.23
     dawned
    1.20
    chy
    1.19
    Activations Density 0.790%

    No Known Activations