© 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. 98899
    Prev
    Next
    INDEX
    Explanations

    Category Archive

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

    This neuron fires on all-caps identifiers (macro names, constants, and other tokens composed of uppercase letters, digits, or underscores).

    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
     Lidé
    -1.01
     recorrido
    -0.91
    裱
    -0.85
    โครง
    -0.81
     žem
    -0.81
     drugiej
    -0.80
    こそ
    -0.79
    ⊑
    -0.78
     bygge
    -0.77
    checkIf
    -0.77
    POSITIVE LOGITS
    unless
    0.92
    ár
    0.86
    czyki
    0.83
     including
    0.79
    ｅ
    0.78
    //
    0.77
     unless
    0.76
     if
    0.75
    #
    0.75
     जिसमें
    0.75
    Activations Density 0.040%

    No Known Activations