© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129839
    Prev
    Next
    INDEX
    Explanations

    shoot yourself in the foot

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

    fire or shoot

    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
    Negative Logits
     Comb
    0.61
    ul
    0.57
    скольку
    0.57
     FeCl
    0.57
    𝚞
    0.55
     Dies
    0.55
     作り
    0.54
     Hakone
    0.54
    вать
    0.54
     Diet
    0.54
    POSITIVE LOGITS
    Firing
    0.83
     fired
    0.82
     firing
    0.75
     shots
    0.69
    Shot
    0.68
    射
    0.68
    fired
    0.68
     bắn
    0.68
    火
    0.68
     shooting
    0.66
    Activations Density 0.335%

    No Known Activations