© 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. 111198
    Prev
    Next
    INDEX
    Explanations

    stabbed with a knife

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

    sharp implements and stabbing actions

    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
     blasting
    0.49
     bombs
    0.48
     गर्ल्स
    0.47
     bombing
    0.47
     bombed
    0.46
     bột
    0.46
    災
    0.46
     bombings
    0.45
     തേ
    0.44
     hạt
    0.44
    POSITIVE LOGITS
     stabbed
    0.81
     stab
    0.73
     knife
    0.72
     dagger
    0.72
    刺
    0.72
     stabbing
    0.68
    stab
    0.64
     piercing
    0.58
    🗡
    0.58
     Knife
    0.57
    Activations Density 0.048%

    No Known Activations