© 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. 6843
    Prev
    Next
    INDEX
    Explanations

    all data, Please click, receive our

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

    This neuron detects formal compliance or disclaimer statements—e.g. data‐availability declarations and registration confirmation instructions.

    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
     hediye
    -0.81
     cappuccino
    -0.80
     Chanel
    -0.80
    ryk
    -0.79
    Usuarios
    -0.79
    chanel
    -0.79
    raptor
    -0.77
    ρω
    -0.77
    Nieuwe
    -0.76
     educativos
    -0.76
    POSITIVE LOGITS
    ˀ
    0.88
     włosy
    0.78
     actuator
    0.77
     штук
    0.75
    OnPage
    0.72
     dubbio
    0.72
     deserto
    0.71
     購入
    0.70
     solito
    0.70
    Pautan
    0.70
    Activations Density 0.006%

    No Known Activations