© 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
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 2832
    Prev
    Next
    INDEX
    Explanations

    for any occasion

    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
    ChangeListener
    1.35
    므로
    1.34
    <0xD2>
    1.32
    ){\
    1.31
    reonine
    1.27
     consecuencias
    1.27
    原因是
    1.26
    avantage
    1.25
    ”
    1.23
    irable
    1.23
    POSITIVE LOGITS
     ANY
    2.73
     any
    2.72
     anytime
    2.41
     Any
    2.36
     ANYTHING
    2.34
     qualsiasi
    2.26
     anywhere
    2.24
    Any
    2.19
     orice
    2.18
     anything
    2.16
    Activations Density 0.658%

    No Known Activations