© 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. 25793
    Prev
    Next
    INDEX
    Explanations

    introduction or poison

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

    The neuron is simply tracking each token’s absolute position in the document—later tokens elicit higher activations.

    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
    ardin
    -0.91
    ␮
    -0.83
     planification
    -0.82
     rellen
    -0.82
    дец
    -0.81
    💳
    -0.79
    PLUGIN
    -0.76
    ★★★★☆
    -0.76
     maximization
    -0.76
     خلا
    -0.75
    POSITIVE LOGITS
     Mal
    0.84
     legumes
    0.76
     stored
    0.76
     Denk
    0.75
     Zer
    0.75
     Boring
    0.73
     萌
    0.69
     panto
    0.69
     vorstellen
    0.69
    Mal
    0.68
    Activations Density 0.010%

    No Known Activations