© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 545
    Prev
    Next
    INDEX
    Explanations

    destroying enemies or discarding items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     chăm
    0.74
    igle
    0.71
     acert
    0.69
    볐
    0.68
     enga
    0.68
    বেশ
    0.68
     thăm
    0.67
     ayudar
    0.65
     atento
    0.65
    늡
    0.65
    POSITIVE LOGITS
     eliminated
    2.82
     abolished
    2.66
     abolish
    2.63
     elimination
    2.62
     removal
    2.61
     discontinuation
    2.60
     abol
    2.59
     disband
    2.58
     removed
    2.58
     discontinu
    2.55
    Activations Density 4.196%

    No Known Activations