© 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. 76222
    Prev
    Next
    INDEX
    Explanations

    book published

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

    The neuron strongly activates on numeric literal tokens (e.g. “256,” “392,” “64,” etc.).

    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
     kullanıcı
    -0.85
    𝗌
    -0.78
    })();
    
    -0.75
     kerana
    -0.74
     empleados
    -0.74
     aquesta
    -0.74
    Билгалдахарш
    -0.73
    这些
    -0.73
     ISD
    -0.73
     ожида
    -0.73
    POSITIVE LOGITS
     guests
    1.05
     today
    0.90
     unfamiliar
    0.89
     guest
    0.89
    guests
    0.88
    Unknown
    0.84
     познакоми
    0.83
    是由
    0.82
     essence
    0.81
     говорил
    0.81
    Activations Density 0.001%

    No Known Activations