© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7747
    Prev
    Next
    INDEX
    Explanations

    survival

    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_12_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
    ptus
    1.61
    geom
    1.58
     susp
    1.57
     delic
    1.54
    ylim
    1.52
    openqa
    1.51
     play
    1.41
    宜
    1.39
     undef
    1.38
     quiet
    1.38
    POSITIVE LOGITS
     náklady
    2.38
     pandemics
    2.21
    occasione
    2.08
     decompositions
    2.03
     colitis
    2.02
    Dijstra
    1.99
    applicazione
    1.98
     generaciones
    1.95
    rän
    1.94
     springfox
    1.93
    Activations Density 0.025%

    No Known Activations