© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130487
    Prev
    Next
    INDEX
    Explanations

    stochastic calculus and processes

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

    The neuron responds strongly to occurrences of the term “stochastic,” especially in technical mathematical contexts.

    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
    ?!!
    -2.33
    柺
    -2.31
    ’?
    -2.31
    !!!!!!!
    -2.23
     hav
    -2.23
    !!!!!!
    -2.20
    !!!!!!!!!
    -2.17
    !!!!!!!!!!
    -2.17
     juft
    -2.17
    ?!?!
    -2.16
    POSITIVE LOGITS
    ]
    2.55
    }}
    2.41
    *
    2.28
    )
    2.20
     pertumbuhan
    2.09
     nimble
    2.08
    ),
    2.05
    </em>
    2.03
    0
    2.02
     []:
    1.98
    Activations Density 0.004%

    No Known Activations