© 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. 77577
    Prev
    Next
    INDEX
    Explanations

    sendTextMessage

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

    The neuron chiefly detects snippets of programming code or code‐like tokens embedded in the text.

    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
    aliana
    -0.86
     헤
    -0.82
     divisive
    -0.79
    pá
    -0.77
    泱
    -0.76
    govina
    -0.75
     estoy
    -0.75
    监测
    -0.74
     soar
    -0.73
     pavements
    -0.73
    POSITIVE LOGITS
     carriers
    0.93
     carrier
    0.86
    AsyncResult
    0.81
     Ericsson
    0.80
    Carrier
    0.80
     subscriber
    0.78
     phone
    0.78
     subscribers
    0.78
     Phone
    0.77
    aphone
    0.76
    Activations Density 0.005%

    No Known Activations