© 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. 82675
    Prev
    Next
    INDEX
    Explanations

    Severe gastric dilatation

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

    Microsoft technical documentation and support content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly responds to numerical identifiers and version/policy numbers (e.g. KB article IDs or setting numbers).

    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
     activiteiten
    -0.90
     üç
    -0.82
     tiga
    -0.81
     deixe
    -0.81
     сегодня
    -0.78
    énez
    -0.78
    Hình
    -0.77
    Па
    -0.77
    şen
    -0.76
    遜
    -0.75
    POSITIVE LOGITS
     Microsoft
    1.03
    Microsoft
    0.93
    http
    0.93
     Symptoms
    0.90
    vodu
    0.84
    theit
    0.84
    gné
    0.82
    PLICATE
    0.79
     redu
    0.79
     überhaupt
    0.79
    Activations Density 0.016%

    No Known Activations