© 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. 3526
    Prev
    Next
    INDEX
    Explanations

    that best suits

    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
     Ono
    1.58
     Bondi
    1.55
    ffen
    1.55
     alien
    1.51
     Oppen
    1.50
     Edd
    1.48
     Astronomical
    1.44
    诱
    1.44
     Alien
    1.44
     Bhat
    1.42
    POSITIVE LOGITS
     finish
    1.22
     finished
    1.15
     finishes
    1.12
     remainder
    1.09
     completion
    1.03
     continuation
    1.01
     lanjutkan
    0.99
     Continuation
    0.98
     Stops
    0.97
     stops
    0.97
    Activations Density 0.055%

    No Known Activations