© 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. 58870
    Prev
    Next
    INDEX
    Explanations

    greetings and names

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

    The neuron fires on valedictions—i.e. the sign-off phrases (like “Regards,” “Love …,” “Thanks,” “XO,” etc.) marking the end of a message.

    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
     now
    -1.08
    ついで
    -1.05
    satunya
    -1.02
    외부
    -0.93
    入り口
    -0.92
    経緯
    -0.92
    巿
    -0.91
     stanga
    -0.89
     misericordia
    -0.88
     größer
    -0.86
    POSITIVE LOGITS
    "./
    1.07
    season
    1.05
    recogn
    1.03
     luzes
    1.02
    lepší
    1.02
     reconhe
    1.02
    Thank
    1.02
    Thanks
    1.02
     ajustable
    1.01
    strictEqual
    1.01
    Activations Density 0.015%

    No Known Activations