© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44711
    Prev
    Next
    INDEX
    Explanations

    continuation across states

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

    The neuron detects terms that signal transfer or continuation across contexts (e.g. carry-over, hold-over, inherited, passed through).

    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
            
    -1.80
         
    -1.58
    ⡪
    -1.52
     или
    -1.49
    bino
    -1.41
    ↵↵
    -1.38
    ка
    -1.35
                 
    -1.34
     dostępne
    -1.33
                               
    -1.32
    POSITIVE LOGITS
     respective
    1.48
    <th>
    1.46
    们的
    1.41
    に於
    1.32
     לת
    1.31
    ("__
    1.30
     Pending
    1.27
    ('../
    1.26
    viembre
    1.25
     berharap
    1.25
    Activations Density 0.063%

    No Known Activations