© 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. 65948
    Prev
    Next
    INDEX
    Explanations

    $this variable access

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

    the neuron detects numeric literal values (number constants) in the code.

    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
    ]$}
    -1.24
     первом
    -1.13
     YEAR
    -1.11
    haviours
    -1.10
     новом
    -1.09
     attribué
    -1.09
    贋
    -1.09
    Tahun
    -1.08
     nena
    -1.08
     смысле
    -1.07
    POSITIVE LOGITS
     it
    1.16
    ‐
    1.11
     this
    1.05
    āja
    1.05
    _
    1.04
    estries
    1.02
     you
    1.01
     einzelnen
    1.00
    ,”
    1.00
     people
    0.99
    Activations Density 0.002%

    No Known Activations