© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59679
    Prev
    Next
    INDEX
    Explanations

    weapons and defense items

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

    The neuron is triggered by terms referring to weapons or security/defense devices (especially non-lethal arms and self-defense tools).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -1.26
    竄
    -1.17
    ÈME
    -1.12
    ÊNCIA
    -1.07
    ine
    -1.04
    いや
    -1.04
    豔
    -1.02
    problem
    -1.02
    ciled
    -1.02
    ᄇ
    -1.00
    POSITIVE LOGITS
    )
    1.18
    ועל
    1.12
     use
    1.09
    );
    1.09
     plupart
    1.07
     envis
    1.06
     curving
    1.05
     tyrants
    1.04
    目安
    1.03
     democra
    1.02
    Activations Density 0.091%

    No Known Activations