© 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. 10-GEMMASCOPE-RES-131K
    7. 103905
    Prev
    Next
    INDEX
    Explanations

    place and rank

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

    The neuron detects mentions of competitive rankings or standings expressed as “place” (e.g. first place, second place, third place).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ’
    -1.96
    étranger
    -1.83
     termed
    -1.80
    aéroport
    -1.75
     związane
    -1.68
     usado
    -1.65
    dersfield
    -1.63
    épreuve
    -1.63
    assemblée
    -1.61
    </td>
    -1.59
    POSITIVE LOGITS
    ="
    2.59
    ?"
    1.99
     ambitions
    1.90
     homicidio
    1.88
    蕺
    1.87
    LLOW
    1.80
    嘿嘿
    1.80
    也就是
    1.80
    哎呀
    1.76
    6
    1.76
    Activations Density 0.006%

    No Known Activations