© 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. 3471
    Prev
    Next
    INDEX
    Explanations

    shadow serpent/aetheria/echoes

    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
    晒
    1.33
    Sunny
    1.32
     Busy
    1.30
    Crazy
    1.28
     Lazy
    1.28
    便利
    1.28
    飽
    1.28
     naughty
    1.27
    炒
    1.26
    ÉS
    1.26
    POSITIVE LOGITS
    realm
    1.69
    iculation
    1.56
    рија
    1.55
    winds
    1.55
    arlock
    1.53
    enski
    1.53
    ćem
    1.52
    闕
    1.49
    řel
    1.48
    reihe
    1.47
    Activations Density 0.266%

    No Known Activations