© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74678
    Prev
    Next
    INDEX
    Explanations

    aiming and optics

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

    The neuron activates on words referring to optical aiming or sighting devices (e.g. sights, sighting, finder, ring).

    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
    irmingham
    -1.44
     bazı
    -1.38
     Sitzung
    -1.38
     Där
    -1.34
     Verfü
    -1.33
     invitado
    -1.33
     payé
    -1.32
    ㄥ
    -1.31
     niektor
    -1.31
     anfitrión
    -1.30
    POSITIVE LOGITS
    ll
    1.44
     ostavi
    1.37
    賅
    1.29
    cluir
    1.25
     formul
    1.23
     Manche
    1.23
     DEPART
    1.22
     of
    1.18
     ilg
    1.18
    didSet
    1.17
    Activations Density 0.012%

    No Known Activations