© 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. 34-GEMMASCOPE-RES-131K
    7. 92552
    Prev
    Next
    INDEX
    Explanations

    words starting with con

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

    The neuron strongly activates on the root “conject” in words like “conjecture,” “conjectured,” and “conjecturally.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     bisschen
    -1.13
     chiara
    -1.13
     greateſt
    -1.10
     uncovering
    -1.09
     conosciuto
    -1.08
     confronto
    -1.07
     consultar
    -1.06
    casas
    -1.05
    läng
    -1.04
     comentario
    -1.02
    POSITIVE LOGITS
     Con
    1.39
     CON
    1.11
    con
    1.11
    tura
    1.09
    </sup>
    1.09
    </h2>
    1.07
    发表于
    1.05
    copg
    1.02
    poran
    1.02
    ↵
    1.00
    Activations Density 0.069%

    No Known Activations