© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8209
    Prev
    Next
    INDEX
    Explanations

    either version

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

    The neuron tends to light up on infrequent or “rare” tokens—e.g. proper names, unusual suffixes, version numbers, and niche legal or interface terms.

    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
     Prüfung
    -0.76
    ویژگی
    -0.74
    rouille
    -0.73
    duga
    -0.72
    arté
    -0.71
    entier
    -0.71
     Präsentation
    -0.70
    clientes
    -0.69
     Zurück
    -0.69
     Betrachtung
    -0.69
    POSITIVE LOGITS
     limão
    0.79
     renovating
    0.77
    seamnă
    0.76
     Ponto
    0.76
    ctuation
    0.75
     Wellesley
    0.73
     Liberation
    0.73
    Tē
    0.73
    глу
    0.72
     liberating
    0.71
    Activations Density 0.004%

    No Known Activations