© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48452
    Prev
    Next
    INDEX
    Explanations

    wanting actions or outcomes

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

    The neuron strongly activates on content verbs (especially base-form and action-oriented verbs).

    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
    tives
    -1.24
     turista
    -1.18
     lamenta
    -1.16
     poitrine
    -1.15
     Meksi
    -1.14
     Lainnya
    -1.14
     configurar
    -1.13
    Ṁ
    -1.13
    katakan
    -1.13
    ganggu
    -1.11
    POSITIVE LOGITS
     be
    1.55
     its
    1.51
     відчу
    1.30
     empieza
    1.27
    zembro
    1.25
    First
    1.23
    3
    1.23
    ,”
    1.23
     primero
    1.20
     zunächst
    1.20
    Activations Density 0.075%

    No Known Activations