© 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. 920
    Prev
    Next
    INDEX
    Explanations

    limits of desired outcomes

    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
     Shipbuilding
    1.09
    changed
    0.84
    CIC
    0.82
    readFile
    0.80
     Cor
    0.80
     Cot
    0.80
    件
    0.80
     Ains
    0.80
     shuffling
    0.80
    Cot
    0.78
    POSITIVE LOGITS
    极限
    2.18
    上限
    2.15
     límite
    2.14
     limits
    2.09
     unreachable
    2.07
     Limits
    2.07
    限界
    2.05
     limit
    2.05
    阈
    2.04
     unattainable
    2.03
    Activations Density 2.130%

    No Known Activations