© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76889
    Prev
    Next
    INDEX
    Explanations

    LOS ANGELES class attack submarine

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

    The neuron is detecting sequences of digits and numeric identifiers (e.g., hull numbers, years, or other code‐style 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
     دریافت‌شده
    -0.74
    poir
    -0.73
     Pristupljeno
    -0.72
     outono
    -0.71
     pós
    -0.71
    кспер
    -0.71
     lavabo
    -0.70
    蟇
    -0.70
     olho
    -0.69
     deed
    -0.68
    POSITIVE LOGITS
     tubes
    0.82
    wife
    0.79
     Smash
    0.78
    lng
    0.77
     wife
    0.77
     tillbaka
    0.77
     Tubes
    0.76
    octet
    0.75
     accep
    0.75
     PST
    0.75
    Activations Density 0.040%

    No Known Activations