© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1337
    Prev
    Next
    INDEX
    Explanations

    retrieving by ID

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

    The neuron detects numeric literals (integer constants) in 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_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
     naming
    -1.05
    understood
    -0.90
     AUTHORITIES
    -0.88
    beads
    -0.88
     dodatk
    -0.86
     defStyleAttr
    -0.86
     dodatkowe
    -0.84
    erati
    -0.82
     додат
    -0.81
    achieved
    -0.81
    POSITIVE LOGITS
     id
    1.03
    PathVariable
    1.02
     searched
    0.93
     sought
    0.91
     parseInt
    0.90
    特定的
    0.88
    ød
    0.87
    searchText
    0.85
     protagonista
    0.82
    chlag
    0.82
    Activations Density 0.011%

    No Known Activations