© 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. 59214
    Prev
    Next
    INDEX
    Explanations

    Speeches, missing, purpose

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

    The neuron spotlights code‐comment linter directives—especially “pylint: disable” annotations.

    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
     toString
    -0.78
     통해
    -0.74
    素晴らしい
    -0.73
     إس
    -0.73
    JsonPropertyName
    -0.71
     tutt
    -0.70
     Psychos
    -0.68
    少しずつ
    -0.67
    Limitations
    -0.67
     sociale
    -0.67
    POSITIVE LOGITS
     Membership
    0.82
     Marta
    0.81
    Ę
    0.81
    カン
    0.80
     Maya
    0.78
     Laurent
    0.77
    epy
    0.77
     Broad
    0.75
    Β
    0.73
     black
    0.73
    Activations Density 0.021%

    No Known Activations