© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5461
    Prev
    Next
    INDEX
    Explanations

    even if / even when

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     confessions
    0.95
    belief
    0.93
    fruits
    0.92
     beliefs
    0.92
     Agencies
    0.91
    ographies
    0.91
     visible
    0.90
    嘘
    0.90
     Bra
    0.88
     necklaces
    0.87
    POSITIVE LOGITS
     bakın
    1.25
     yapacağız
    1.24
     fornisce
    1.23
     bunu
    1.22
     chce
    1.21
     hiệp
    1.20
     sempl
    1.18
     wprowad
    1.17
     izgrad
    1.17
     fornece
    1.17
    Activations Density 0.102%

    No Known Activations