© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19177
    Prev
    Next
    INDEX
    Explanations

    remove / delete

    np_acts-logits-general · gemini-2.5-flash-lite

    file removal or deletion operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     জড়
    0.42
    ㄲ
    0.39
     spasm
    0.39
     سینٹی
    0.39
    ╫
    0.38
    rocery
    0.38
     trich
    0.38
    اعه
    0.37
    <0x92>
    0.37
    矮
    0.37
    POSITIVE LOGITS
    Remove
    0.68
     remove
    0.67
    删除
    0.66
    remove
    0.65
     Remove
    0.63
     removes
    0.63
     removed
    0.61
     remover
    0.61
     deletes
    0.61
    移除
    0.60
    Activations Density 0.013%

    No Known Activations