© 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. 67830
    Prev
    Next
    INDEX
    Explanations

    firearm or transducer

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

    The neuron consistently activates on mentions of concrete instruments or devices (e.g., “firearm,” “transducer”).

    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
     were
    -2.80
    s
    -2.53
    -
    -2.41
     the
    -2.33
    乄
    -2.31
     immédiatement
    -2.30
    while
    -2.25
    ate
    -2.25
     entrepreneurial
    -2.23
     Conſ
    -2.23
    POSITIVE LOGITS
     (‘
    2.38
     født
    2.30
     They
    2.28
     indicating
    2.23
     alltså
    2.22
     могло
    2.14
     whereby
    2.09
     если
    2.09
     varför
    2.09
     stating
    2.06
    Activations Density 0.072%

    No Known Activations