© 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. 118233
    Prev
    Next
    INDEX
    Explanations

    Revital, meet, widespread, made, Jan, Category

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

    This neuron is tracking the token’s position in the document, with activation rising roughly in step with the token index.

    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
     profilo
    -0.95
    ONIC
    -0.89
     сделал
    -0.87
     concetto
    -0.82
    concepto
    -0.79
    orting
    -0.79
     MISSION
    -0.79
    Noticia
    -0.79
    レール
    -0.79
     guider
    -0.78
    POSITIVE LOGITS
     пу
    0.84
    SIP
    0.82
     необходимо
    0.79
     ·
    0.79
    }_{
    0.76
    蓉
    0.75
    Preliminaries
    0.75
     capable
    0.73
    麟
    0.73
     contents
    0.73
    Activations Density 0.031%

    No Known Activations