© 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. 22-GEMMASCOPE-RES-131K
    7. 72729
    Prev
    Next
    INDEX
    Explanations

    observed actions

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

    The neuron fires strongly on bare‐form, simple present‐tense action verbs (e.g. “obey,” “get,” “grow,” “speak,” “arrive,” “appear”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     you
    -1.32
     we
    -1.18
     are
    -1.18
    让
    -1.16
     tìm
    -1.16
    V
    -1.14
    im
    -1.14
     to
    -1.12
    F
    -1.12
     have
    -1.10
    POSITIVE LOGITS
    ÁB
    1.33
    𒊹
    1.30
     sereia
    1.20
    Specifik
    1.20
    Febru
    1.20
    宬
    1.19
    Oferta
    1.16
    itizing
    1.16
     bandeja
    1.14
    Ilustra
    1.14
    Activations Density 0.039%

    No Known Activations