© 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. 5250
    Prev
    Next
    INDEX
    Explanations

    execute or open

    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
     reales
    1.71
    솟
    1.51
    pliers
    1.33
     그런
    1.30
     wrongs
    1.28
     olmuş
    1.28
     그거
    1.27
    척
    1.25
    덜
    1.22
    ovati
    1.22
    POSITIVE LOGITS
     ahead
    2.06
     Ahead
    1.99
    ahead
    1.82
     Info
    1.73
     Information
    1.58
    iapan
    1.58
     information
    1.58
    Ahead
    1.57
     Genealogy
    1.56
    が必要です
    1.54
    Activations Density 0.134%

    No Known Activations