© 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. 69971
    Prev
    Next
    INDEX
    Explanations

    actions followed by appropriately

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

    The neuron responds to technical or procedural terms that denote adjusting, configuring, or measuring (e.g., “adjusted,” “update,” “modify,” “controls,” “penalized,” “plan”).

    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
     prolon
    -0.85
     altså
    -0.85
     یہ
    -0.84
     ועוד
    -0.84
    tka
    -0.81
     hombro
    -0.80
    érique
    -0.79
    因為
    -0.78
    StoreMessageInfo
    -0.76
     یعنی
    -0.76
    POSITIVE LOGITS
     accordingly
    7.88
    Accordingly
    5.78
     Accordingly
    5.78
     соответственно
    3.73
     correspondingly
    3.73
     consequently
    3.50
     entsprechend
    3.23
    Consequently
    3.16
     Consequently
    3.05
     відповід
    2.78
    Activations Density 0.152%

    No Known Activations